Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Infinite Photorealistic Worlds using Procedural Generation paper page: introduce Infinigen, a procedural generator of photorealistic 3D scenes of the natural world. Infinigen is entirely procedural: every asset, from shape to texture, is generated from scratch via randomized mathematical rules, using no external source and allowing infinite variation and composition....

_akhaliq's profile picture

AK

515,387 subscribers

275,403 Aufrufe • vor 3 Jahren •via X (Twitter)

BildungKunstWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von AK
AKvor 3 Jahren

github:

Profilbild von bellicose_bestie
bellicose_bestievor 3 Jahren

Are research labs just publishing procedural algorithm work as "ai" on hugging face (aside from just arxiv) just to get more exposure?

Profilbild von Xenofy🛸👽
Xenofy🛸👽vor 3 Jahren

@JCorvinusVR

Profilbild von burgesst 🗿🪣
burgesst 🗿🪣vor 3 Jahren

How the hell do you define a chameleon procedurally?

Profilbild von Sir Mr Meow Meow
Sir Mr Meow Meowvor 3 Jahren

wow getting pretty amazing tbh

Profilbild von baloblack
baloblackvor 3 Jahren

👍🏾

Profilbild von Stalin Kay
Stalin Kayvor 3 Jahren

@readwise save thread

Profilbild von 0ptim
0ptimvor 3 Jahren

Hey Sean, this might be of interest to you. @NoMansSky

Profilbild von Ivan Parfenchuk
Ivan Parfenchukvor 3 Jahren

Infinigen Twitch stream soon?

Profilbild von John R. Lawson 🌦
John R. Lawson 🌦vor 3 Jahren

We're in the Computational Universe, after all.

Ähnliche Videos

Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video Contribution quote from the paper: In summary, our main contributions are • a comprehensive pipeline for reconstructing the shape, appearance, and behavior of real-world garments using Gaussian splatting, • an algorithm for registering garment meshes to multi- view videos with an optimization procedure based on Gaussian splatting, and • a Gaussian Garment representation that combines triangle meshes with Gaussian textures to capture photorealistic appearance and can be used as a fully controllable 3D asset.
0:20

Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video Contribution quote from the paper: In summary, our main contributions are • a comprehensive pipeline for reconstructing the shape, appearance, and behavior of real-world garments using Gaussian splatting, • an algorithm for registering garment meshes to multi- view videos with an optimization procedure based on Gaussian splatting, and • a Gaussian Garment representation that combines triangle meshes with Gaussian textures to capture photorealistic appearance and can be used as a fully controllable 3D asset.

MrNeRF

27,345 Aufrufe • vor 1 Jahr

This might be the craziest workflow you'll see this week. From #VR greyboxing to 3D worlds with the help of #AI. The 2 tools I used are ShapesXR and Marble from World Labs. Let me tell you why and how. - ShapesXR is the most powerful and fastest way to assemble 3D scenes at scale. - The library of assets + ability to sketch from procedural primitives gives the perfect balance between speed and freedom. - ShapesXR allows you to export your creation as a glTF that can be used as a "3D prompt" into Marble - Marble now allows you to create a panorama using a 3D scene as input increasing DRAMATICALLY the control you have during the creation process - Through the workflow you can adjust textures and objects in the scene using AI inpainting - There are tons of options on how to use the final output (create a #GaussianSplatting, export collision mesh and even a detailed mesh 🤯) This is the perfect examples of how VR creative tools improve and accelerate the design process... so make sure to follow me if that's your jam 😉.
1:01

This might be the craziest workflow you'll see this week. From #VR greyboxing to 3D worlds with the help of #AI. The 2 tools I used are ShapesXR and Marble from World Labs. Let me tell you why and how. - ShapesXR is the most powerful and fastest way to assemble 3D scenes at scale. - The library of assets + ability to sketch from procedural primitives gives the perfect balance between speed and freedom. - ShapesXR allows you to export your creation as a glTF that can be used as a "3D prompt" into Marble - Marble now allows you to create a panorama using a 3D scene as input increasing DRAMATICALLY the control you have during the creation process - Through the workflow you can adjust textures and objects in the scene using AI inpainting - There are tons of options on how to use the final output (create a #GaussianSplatting, export collision mesh and even a detailed mesh 🤯) This is the perfect examples of how VR creative tools improve and accelerate the design process... so make sure to follow me if that's your jam 😉.

Gabriele Romagnoli

20,126 Aufrufe • vor 9 Monaten

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.
0:34

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

AK

305,663 Aufrufe • vor 3 Jahren

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!
2:41

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

Santiago

65,446 Aufrufe • vor 3 Monaten

Tracking Anything with Decoupled Video Segmentation paper page: Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation.
0:32

Tracking Anything with Decoupled Video Segmentation paper page: Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation.

AK

305,683 Aufrufe • vor 2 Jahren

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.
0:50

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,798 Aufrufe • vor 3 Jahren

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.
0:22

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.

MrNeRF

42,553 Aufrufe • vor 1 Jahr

✨We are excited to open-source Tencent HY-Motion 1.0, a billion-parameter text-to-motion model built on the Diffusion Transformer (DiT) architecture and flow matching. Tencent HY-Motion 1.0 empowers developers and individual creators alike by transforming natural language into high-fidelity, fluid, and diverse 3D character animations, delivering exceptional instruction-following capabilities across a broad range of categories. The generated 3D animation assets can be seamlessly integrated into typical 3D animation pipelines.🎮🎥 Highlights: 🔹Billion-Scale DiT: Successfully scaled flow-matching DiT to 1B+ parameters, setting a new ceiling for instruction-following capability and generated motion quality. 🔹Full-Stage Training Strategy: The industry’s first motion generation model featuring a complete Pre-training → SFT → RL loop to optimize physical plausibility and semantic accuracy. 🔹Comprehensive Category Coverage: Features 200+ motion categories across 6 major classes—the most comprehensive in the industry, curated via a meticulous data pipeline. 🌐Project Page: 🔗Github: 🤗Hugging Face: 📄Technical report:
1:15

✨We are excited to open-source Tencent HY-Motion 1.0, a billion-parameter text-to-motion model built on the Diffusion Transformer (DiT) architecture and flow matching. Tencent HY-Motion 1.0 empowers developers and individual creators alike by transforming natural language into high-fidelity, fluid, and diverse 3D character animations, delivering exceptional instruction-following capabilities across a broad range of categories. The generated 3D animation assets can be seamlessly integrated into typical 3D animation pipelines.🎮🎥 Highlights: 🔹Billion-Scale DiT: Successfully scaled flow-matching DiT to 1B+ parameters, setting a new ceiling for instruction-following capability and generated motion quality. 🔹Full-Stage Training Strategy: The industry’s first motion generation model featuring a complete Pre-training → SFT → RL loop to optimize physical plausibility and semantic accuracy. 🔹Comprehensive Category Coverage: Features 200+ motion categories across 6 major classes—the most comprehensive in the industry, curated via a meticulous data pipeline. 🌐Project Page: 🔗Github: 🤗Hugging Face: 📄Technical report:

Tencent Hy

328,874 Aufrufe • vor 7 Monaten

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.
0:33

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

AK

122,560 Aufrufe • vor 3 Jahren

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.
0:42

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.

AK

62,768 Aufrufe • vor 3 Jahren

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives paper page: Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fidelity 3D scenes, we focus on parsing a scene into mid-level 3D representations made of a small set of textured primitives. Such representations are interpretable, easy to manipulate and suited for physics-based simulations. Moreover, unlike existing primitive decomposition methods that rely on 3D input data, our approach operates directly on images through differentiable rendering. Specifically, we model primitives as textured superquadric meshes and optimize their parameters from scratch with an image rendering loss. We highlight the importance of modeling transparency for each primitive, which is critical for optimization and also enables handling varying numbers of primitives. We show that the resulting textured primitives faithfully reconstruct the input images and accurately model the visible 3D points, while providing amodal shape completions of unseen object regions. We compare our approach to the state of the art on diverse scenes from DTU, and demonstrate its robustness on real-life captures from BlendedMVS and Nerfstudio. We also showcase how our results can be used to effortlessly edit a scene or perform physical simulations.
0:27

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives paper page: Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fidelity 3D scenes, we focus on parsing a scene into mid-level 3D representations made of a small set of textured primitives. Such representations are interpretable, easy to manipulate and suited for physics-based simulations. Moreover, unlike existing primitive decomposition methods that rely on 3D input data, our approach operates directly on images through differentiable rendering. Specifically, we model primitives as textured superquadric meshes and optimize their parameters from scratch with an image rendering loss. We highlight the importance of modeling transparency for each primitive, which is critical for optimization and also enables handling varying numbers of primitives. We show that the resulting textured primitives faithfully reconstruct the input images and accurately model the visible 3D points, while providing amodal shape completions of unseen object regions. We compare our approach to the state of the art on diverse scenes from DTU, and demonstrate its robustness on real-life captures from BlendedMVS and Nerfstudio. We also showcase how our results can be used to effortlessly edit a scene or perform physical simulations.

AK

38,571 Aufrufe • vor 3 Jahren

Generative AI is cool and all, but procedural 3D modeling just hits different. Check out this Houdini setup by Pepe Buendia. Why this is cool: Instead of manually placing every building and car, this system generates an NYC-style city that builds itself -- automatically spawning buildings with unique variations, plus a traffic system where cars actually obey traffic lights and avoid crashing into each other (all orchestrated through houdini VEX code). Each car knows exactly which road it's on and makes real-time decisions about navigation. The whole thing runs on custom algorithms that handle everything from road directions to building placement. If you did this with generative AI, even approaches to conditioning and taming the chaos -- you'd still get a ton of variance which might be an issue for visual and spatial consistency. To me this is procedural modeling at its finest - precise control meets infinite scalability. Immensely useful for media & entertainment, but also synthetic training data for robotics and augmented reality. I of course can't wait until multimodal LLMs to have the spatial understanding to write these kind of controllable 3D worlds for us. Claude counting 2D pixels on a screen is a step in this direction. Soon they'll be able to manipulate 2D ortho viewports, and eventually spawn procedural 3D worlds.
0:24

Generative AI is cool and all, but procedural 3D modeling just hits different. Check out this Houdini setup by Pepe Buendia. Why this is cool: Instead of manually placing every building and car, this system generates an NYC-style city that builds itself -- automatically spawning buildings with unique variations, plus a traffic system where cars actually obey traffic lights and avoid crashing into each other (all orchestrated through houdini VEX code). Each car knows exactly which road it's on and makes real-time decisions about navigation. The whole thing runs on custom algorithms that handle everything from road directions to building placement. If you did this with generative AI, even approaches to conditioning and taming the chaos -- you'd still get a ton of variance which might be an issue for visual and spatial consistency. To me this is procedural modeling at its finest - precise control meets infinite scalability. Immensely useful for media & entertainment, but also synthetic training data for robotics and augmented reality. I of course can't wait until multimodal LLMs to have the spatial understanding to write these kind of controllable 3D worlds for us. Claude counting 2D pixels on a screen is a step in this direction. Soon they'll be able to manipulate 2D ortho viewports, and eventually spawn procedural 3D worlds.

Bilawal Sidhu

527,494 Aufrufe • vor 1 Jahr

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation.
2:32

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation.

AK

161,530 Aufrufe • vor 2 Jahren

I've been a proponent of the idea of combining 3d and generative ai for a long time - as a way to get the best of both worlds: The precision and control of 3d - the detail, realism, lighting and speed of generative models. Here's another example of that idea, realized through a procedural system - entirely vibe-coded with Fable. Inspired by a photograph I took of an old tower in a town in southern France. In the first part of the video I'm using Krea AI's realtime model - later examples show how Nano Banana 2 can be used to take 3d stills and transform them to pretty much anything. What do you think of workflows like this compared to purely generating video or images from text, image or video input?
0:34

I've been a proponent of the idea of combining 3d and generative ai for a long time - as a way to get the best of both worlds: The precision and control of 3d - the detail, realism, lighting and speed of generative models. Here's another example of that idea, realized through a procedural system - entirely vibe-coded with Fable. Inspired by a photograph I took of an old tower in a town in southern France. In the first part of the video I'm using Krea AI's realtime model - later examples show how Nano Banana 2 can be used to take 3d stills and transform them to pretty much anything. What do you think of workflows like this compared to purely generating video or images from text, image or video input?

Martin Nebelong

20,265 Aufrufe • vor 14 Tagen

SpiRobs morphologically replicate the logarithmic spiral that is ubiquitous in natural organisms. They are easy and fast to build across scales via 3D printing. They are actuated by cables, which allow for fast and life-like movements. Besides, a single robot can handle a wide variety of objects (in terms of size, shape, and weight). A key to this is a bioinspired grasping strategy that is found in the octopus. Finally, this work demonstrates a wide range of prototypes, including a miniaturized gripper, a manipulator mounted on a drone, and multi-robot arrays that can grasp in a tendril-like fashion. Authors: Zhanchi Wang, Nikolaos M. Freris, and Xi Wei University of Science and Technology of China Video Credit: ———————————————— Stay ahead of the curve! Follow more cutting edge robotics content, including research, reports and articles on Wevolver:
0:33

SpiRobs morphologically replicate the logarithmic spiral that is ubiquitous in natural organisms. They are easy and fast to build across scales via 3D printing. They are actuated by cables, which allow for fast and life-like movements. Besides, a single robot can handle a wide variety of objects (in terms of size, shape, and weight). A key to this is a bioinspired grasping strategy that is found in the octopus. Finally, this work demonstrates a wide range of prototypes, including a miniaturized gripper, a manipulator mounted on a drone, and multi-robot arrays that can grasp in a tendril-like fashion. Authors: Zhanchi Wang, Nikolaos M. Freris, and Xi Wei University of Science and Technology of China Video Credit: ———————————————— Stay ahead of the curve! Follow more cutting edge robotics content, including research, reports and articles on Wevolver:

Wevolver

23,154 Aufrufe • vor 1 Jahr

Fei-Fei Li ( Fei-Fei Li ) beautifully explains Robotics. She defines robotics not by form, like humanoids or cars, but by function: they are any "embodied machines" that must perceive, understand, and act within a physical, 3D space. This core requirement is "spatial intelligence," the unifying principle of all robotics, allowing them to perform tasks and even collaborate with humans. Throughout all of human history, we have been confined to a single, shared reality: the "physical Earth 3D world." This singularity has been our only playground. However, new technologies that combine 3D generation and reconstruction are shattering this limitation. We can now create "infinite universes"—a multiverse of digital worlds for countless purposes, from training robots to enabling creativity, travel, and storytelling. This leap from one physical world to an infinite multiverse unlocks boundless possibilities for human imagination and interaction. Video from a16z
1:25

Fei-Fei Li ( Fei-Fei Li ) beautifully explains Robotics. She defines robotics not by form, like humanoids or cars, but by function: they are any "embodied machines" that must perceive, understand, and act within a physical, 3D space. This core requirement is "spatial intelligence," the unifying principle of all robotics, allowing them to perform tasks and even collaborate with humans. Throughout all of human history, we have been confined to a single, shared reality: the "physical Earth 3D world." This singularity has been our only playground. However, new technologies that combine 3D generation and reconstruction are shattering this limitation. We can now create "infinite universes"—a multiverse of digital worlds for countless purposes, from training robots to enabling creativity, travel, and storytelling. This leap from one physical world to an infinite multiverse unlocks boundless possibilities for human imagination and interaction. Video from a16z

Rohan Paul

41,441 Aufrufe • vor 7 Monaten

Fei-Fei Li ( Fei-Fei Li ) beautifully explains Robotics. She defines robotics not by form, like humanoids or cars, but by function: they are any "embodied machines" that must perceive, understand, and act within a physical, 3D space. This core requirement is "spatial intelligence," the unifying principle of all robotics, allowing them to perform tasks and even collaborate with humans. Throughout all of human history, we have been confined to a single, shared reality: the "physical Earth 3D world." This singularity has been our only playground. However, new technologies that combine 3D generation and reconstruction are shattering this limitation. We can now create "infinite universes"—a multiverse of digital worlds for countless purposes, from training robots to enabling creativity, travel, and storytelling. This leap from one physical world to an infinite multiverse unlocks boundless possibilities for human imagination and interaction. Video from a16z
1:25

Fei-Fei Li ( Fei-Fei Li ) beautifully explains Robotics. She defines robotics not by form, like humanoids or cars, but by function: they are any "embodied machines" that must perceive, understand, and act within a physical, 3D space. This core requirement is "spatial intelligence," the unifying principle of all robotics, allowing them to perform tasks and even collaborate with humans. Throughout all of human history, we have been confined to a single, shared reality: the "physical Earth 3D world." This singularity has been our only playground. However, new technologies that combine 3D generation and reconstruction are shattering this limitation. We can now create "infinite universes"—a multiverse of digital worlds for countless purposes, from training robots to enabling creativity, travel, and storytelling. This leap from one physical world to an infinite multiverse unlocks boundless possibilities for human imagination and interaction. Video from a16z

Rohan Paul

51,174 Aufrufe • vor 3 Monaten

It’s long been a dream of roboticists to be able to teach a robot in simulation so as to skip the long and expensive process of collecting large amounts of real-world training data. However, building simulations for robot tasks is extremely hard. Ideally, we could go from real data to a useful simulation. This is exactly what Guangqi Jiang and his co-authors do. they use 3d Gaussian splatting to reconstructed scenes which let them create interactive environments that, when combined with a physcs engine, allow for training robot policies that show zero-shot sim-to-real transfer (i.e., using no real-world demonstrations). To learn more, watch Episode 56 of Robopapers with Michael Cho - Rbt/Acc and Chris Paxton now!
46:05

It’s long been a dream of roboticists to be able to teach a robot in simulation so as to skip the long and expensive process of collecting large amounts of real-world training data. However, building simulations for robot tasks is extremely hard. Ideally, we could go from real data to a useful simulation. This is exactly what Guangqi Jiang and his co-authors do. they use 3d Gaussian splatting to reconstructed scenes which let them create interactive environments that, when combined with a physcs engine, allow for training robot policies that show zero-shot sim-to-real transfer (i.e., using no real-world demonstrations). To learn more, watch Episode 56 of Robopapers with Michael Cho - Rbt/Acc and Chris Paxton now!

RoboPapers

20,434 Aufrufe • vor 7 Monaten

AI + robotics research is starting to pick up steam. We can now instruct Spot using natural language using Language-guided Skill Coordination (LSC). A user provides a natural language instruction: "Bring me the chocolates box, cereal box, and pill bottle, and put them on the bedroom table" and the robot navigates to the location of the target objects and places them on the room table. Current versions of Spot rely on a fixed-set vocabulary that cannot generalize to diverse instructions. In this demo, the researchers presented a method that uses large language models to receive a free-form natural language instruction for object rearrangement, which it then executes. It combines: -A voice-to-text model that processes the instructions into text -An LLM that converts natural language instruction to call a library of skills -A perception module that provides ground truth locations and visual object detection And what your left with is a glimpse into what our future will hold: robots executing tasks from human voice prompts.
0:30

AI + robotics research is starting to pick up steam. We can now instruct Spot using natural language using Language-guided Skill Coordination (LSC). A user provides a natural language instruction: "Bring me the chocolates box, cereal box, and pill bottle, and put them on the bedroom table" and the robot navigates to the location of the target objects and places them on the room table. Current versions of Spot rely on a fixed-set vocabulary that cannot generalize to diverse instructions. In this demo, the researchers presented a method that uses large language models to receive a free-form natural language instruction for object rearrangement, which it then executes. It combines: -A voice-to-text model that processes the instructions into text -An LLM that converts natural language instruction to call a library of skills -A perception module that provides ground truth locations and visual object detection And what your left with is a glimpse into what our future will hold: robots executing tasks from human voice prompts.

AI Breakfast

33,725 Aufrufe • vor 3 Jahren