Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

🚨 ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning RGB-D images -> 3D scene-graphs -> enhance with vision-language features Enables a wide range of perception and planning abilities. Deployed in many real-world use-cases.

Krishna Murthy

4,776 subscribers

75,593 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Krishna Murthy

Krishna Murthyvor 2 Jahren

We designed a 3D mapping pipeline that takes in posed RGB-D images and builds an object-based map. Each object in the map is augmented with multi-view fused CLIP features and language descriptions. We build a scene graph; which can easily be parsed by LLMs

Profilbild von Krishna Murthy

Krishna Murthyvor 2 Jahren

Text queries can be abstract / complex. We ask our robot to find "something that goes well with a Ronald MacDonald outfit", and it finds a pair of "red and white sneakers"

Profilbild von Krishna Murthy

Krishna Murthyvor 2 Jahren

We can also identify misplaced objects in the scene graph and search for them. Here, we move the shoes away from the earlier location. The robot then begins searching for plausible locations for the red-white sneakers, and finds them at a nearby shoerack

Profilbild von Krishna Murthy

Krishna Murthyvor 2 Jahren

Another query: "Something to wear for a space party" Finds a t-shirt that has NASA written on it

Profilbild von Krishna Murthy

Krishna Murthyvor 2 Jahren

Queries can involve both text and image context. Show the robot a photograph of Michael Jordan, and ask it to go to "something this guy would play with" The robot finds a nearby basketball

Profilbild von Krishna Murthy

Krishna Murthyvor 2 Jahren

Another example. Here, a handwritten note that reads "go to the laundry bag" indicates to the robot its target location.

Profilbild von Krishna Murthy

Krishna Murthyvor 2 Jahren

This time, a mobile manipulation task, where a Spot mini has to pick up "something healthy to eat". It picks up a plastic mango

Profilbild von Krishna Murthy

Krishna Murthyvor 2 Jahren

"My wrist hurts from using my screwdriver all day. Anything to help?" Robot finds a power drill

Profilbild von Krishna Murthy

Krishna Murthyvor 2 Jahren

We implement a particle-filter based localization approach using per-object CLIP features. This helps us relocalize against a prebuilt map; identify and add new objects to the map; and detect objects that no longer exist in the scene.

Profilbild von Krishna Murthy

Krishna Murthyvor 2 Jahren

We're excited about the prospects ConceptGraphs brings about! Great fun collab: HUGE shoutout to @qiaogu1997 @alihkw_ @SachaMori without whom this work wouldn't have taken the shape it has w/ @bipashasen31 @skymanaditya1 @duckietown_coo @florian_shkurti and many others

Profilbild von Krishna Murthy

Krishna Murthyvor 2 Jahren

ConceptGraphs significantly improves upon ConceptFusion ( making it possible to scale to larger scenes, run inference on-board CPUs, and handles more complex queries. Find Ali's short explainer video at:

Ähnliche Videos

LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM LEGO-SLAM running at 15 FPS on a ScanNet scene with language-based loop closing for drift correction. LEGO-SLAM is a 3DGS-based SLAM framework that supports open-vocabulary semantic querying and rendering. It tracks via G-ICP and efficiently builds a map by embedding Gaussians with scene-adaptive 16D language features. Map management is achieved through Language Pruning and Language-Based Loop Detection. The generated map enables open-vocabulary 3D Object Localization.

LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM LEGO-SLAM running at 15 FPS on a ScanNet scene with language-based loop closing for drift correction. LEGO-SLAM is a 3DGS-based SLAM framework that supports open-vocabulary semantic querying and rendering. It tracks via G-ICP and efficiently builds a map by embedding Gaussians with scene-adaptive 16D language features. Map management is achieved through Language Pruning and Language-Based Loop Detection. The generated map enables open-vocabulary 3D Object Localization.

Ryohei Sasaki@engineer

15,060 Aufrufe • vor 4 Monaten

Chain-of-thought reasoning is a powerful tool to enable language models to work through complex problems. Can we use this with robots? With embodied chain-of-thought, vision-language-action (VLA) models can think through perception and planning! A 🧵👇

Chain-of-thought reasoning is a powerful tool to enable language models to work through complex problems. Can we use this with robots? With embodied chain-of-thought, vision-language-action (VLA) models can think through perception and planning! A 🧵👇

Sergey Levine

30,388 Aufrufe • vor 2 Jahren

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

AK

41,736 Aufrufe • vor 1 Jahr

SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians Contributions: • We propose SuperGSeg: a 3D segmentation method with neural Gaussians, designed to learn hierarchical instance segmentation features from 2D foundation models. • We introduce the concept of Super-Gaussian, a novel representation that integrates hierarchical instance segmentation features, enabling the embedding of high-dimensional language features. This approach addresses previously unfeasible challenges in representing complex scenes with rich semantic details. • Extensive experiments on the LERF-OVS and ScanNet datasets demonstrate the effectiveness of the proposed method, achieving significant improvements in open-vocabulary 3D object-level and scene-level semantic segmentation. It shows particular strength in capturing fine-grained scene details and dense pixel semantic segmentation tasks for the first time.

SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians Contributions: • We propose SuperGSeg: a 3D segmentation method with neural Gaussians, designed to learn hierarchical instance segmentation features from 2D foundation models. • We introduce the concept of Super-Gaussian, a novel representation that integrates hierarchical instance segmentation features, enabling the embedding of high-dimensional language features. This approach addresses previously unfeasible challenges in representing complex scenes with rich semantic details. • Extensive experiments on the LERF-OVS and ScanNet datasets demonstrate the effectiveness of the proposed method, achieving significant improvements in open-vocabulary 3D object-level and scene-level semantic segmentation. It shows particular strength in capturing fine-grained scene details and dense pixel semantic segmentation tasks for the first time.

MrNeRF

13,594 Aufrufe • vor 1 Jahr

📢Panoptic Lifting for 3D Scene Understanding with Neural Fields #CVPR23 highlight! Given only posed RGB images of a scene, we optimize a panoptic radiance field representing color, depth, semantics, and instances at any point in space. Vid: Yawar Siddiqui

📢Panoptic Lifting for 3D Scene Understanding with Neural Fields #CVPR23 highlight! Given only posed RGB images of a scene, we optimize a panoptic radiance field representing color, depth, semantics, and instances at any point in space. Vid: Yawar Siddiqui

Matthias Niessner

29,830 Aufrufe • vor 3 Jahren

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS Contributions: • LangSplatV2 achieves real-time performance with 476.2 FPS for high-dimensional feature splatting and 384.6 FPS for 3D open-vocabulary text querying. • Delivers a 42× speedup and 47× boost in performance compared to LangSplat. • Improves query accuracy while drastically reducing inference time. • Replaces the heavyweight decoder in LangSplat with a sparse coefficient field, removing the main performance bottleneck. • Introduces a CUDA-optimized sparse coefficient splatting method, enabling fast and high-quality rendering of high-dimensional features. • Enables scalable 3D language interaction in complex scenes, opening up real-time applications previously not possible with LangSplat.

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS Contributions: • LangSplatV2 achieves real-time performance with 476.2 FPS for high-dimensional feature splatting and 384.6 FPS for 3D open-vocabulary text querying. • Delivers a 42× speedup and 47× boost in performance compared to LangSplat. • Improves query accuracy while drastically reducing inference time. • Replaces the heavyweight decoder in LangSplat with a sparse coefficient field, removing the main performance bottleneck. • Introduces a CUDA-optimized sparse coefficient splatting method, enabling fast and high-quality rendering of high-dimensional features. • Enables scalable 3D language interaction in complex scenes, opening up real-time applications previously not possible with LangSplat.

MrNeRF

14,261 Aufrufe • vor 1 Jahr

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

AI at Meta

17,858 Aufrufe • vor 8 Monaten

🎤🎤 Excited to introduce COME-robot🤖🤖, Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V. It is the first closed-loop framework utilizing the vision-language foundation model for open-ended reasoning and adaptive planning in real-world scenarios. COME-robot demonstrates a significant improvement in task success rate (~25%) compared to SOTA methods. Project: Arxiv:

🎤🎤 Excited to introduce COME-robot🤖🤖, Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V. It is the first closed-loop framework utilizing the vision-language foundation model for open-ended reasoning and adaptive planning in real-world scenarios. COME-robot demonstrates a significant improvement in task success rate (~25%) compared to SOTA methods. Project: Arxiv:

Siyuan Huang

22,291 Aufrufe • vor 2 Jahren

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

AI at Meta

163,313 Aufrufe • vor 1 Jahr

SceneScript treats 3D reconstruction as a language problem rather than a geometry one. The model watches a video of a room and just learns to write a script for it. It autoregressively spits out text commands like make_wall(...) or make_bbox(...) that define the scene. Stanford's new "Scene Language" paper goes a step further adding CLIP embeddings to capture visual appearance too. The fact that language models already understand spatial relationships well enough to write out scene graphs is pretty wild.

SceneScript treats 3D reconstruction as a language problem rather than a geometry one. The model watches a video of a room and just learns to write a script for it. It autoregressively spits out text commands like make_wall(...) or make_bbox(...) that define the scene. Stanford's new "Scene Language" paper goes a step further adding CLIP embeddings to capture visual appearance too. The fact that language models already understand spatial relationships well enough to write out scene graphs is pretty wild.

Bilawal Sidhu

107,060 Aufrufe • vor 1 Jahr

.介添 shared with us the Game Development Club project, a 3D recreation of an in-game scene, which features a large number of assets, sharing useful skills that help enhance the visual impact of surfaces and methods that add realism to the scene. Read the interview:

.介添 shared with us the Game Development Club project, a 3D recreation of an in-game scene, which features a large number of assets, sharing useful skills that help enhance the visual impact of surfaces and methods that add realism to the scene. Read the interview:

80 LEVEL

18,262 Aufrufe • vor 1 Jahr

Excited to share this demo from Over the Reality! Watch our Unitree Go2 robodog navigating our office while reconstructing the 3D space in real-time using the VGGT-based foundation vision model. This is a prime example of machine perception in action, turning raw RGB camera feeds into rich, detailed 3D maps! The robodog's RGB cam generates a dense, textured 3D reconstruction via VGGT from a few photograms, capturing nuances like object shapes and surfaces with impressive fidelity (main view). Compare that to the standard LiDAR system (top right), it's sparser, more point-cloud focused, lacking the visual richness. Vision models are closing the gap fast! What's powering this? VGGT, a cutting-edge foundation model for 3D perception, trained on datasets orders of magnitude smaller than our massive OVER 3D maps dataset. Imagine the leap when we apply OVER's scale to VGGT-like transformer based architectures, denser reconstructions, better generalization, revolutionary for robotics, machine perception & AR! Stay tuned for more breakthroughs at the intersection of AI, robotics, and DePIN. We're building the future of Physical AI and Spatial Computing at Over the Reality 🌐 What do you think, ready for robodogs in your world? Drop your thoughts! 🤖🌐

Excited to share this demo from Over the Reality! Watch our Unitree Go2 robodog navigating our office while reconstructing the 3D space in real-time using the VGGT-based foundation vision model. This is a prime example of machine perception in action, turning raw RGB camera feeds into rich, detailed 3D maps! The robodog's RGB cam generates a dense, textured 3D reconstruction via VGGT from a few photograms, capturing nuances like object shapes and surfaces with impressive fidelity (main view). Compare that to the standard LiDAR system (top right), it's sparser, more point-cloud focused, lacking the visual richness. Vision models are closing the gap fast! What's powering this? VGGT, a cutting-edge foundation model for 3D perception, trained on datasets orders of magnitude smaller than our massive OVER 3D maps dataset. Imagine the leap when we apply OVER's scale to VGGT-like transformer based architectures, denser reconstructions, better generalization, revolutionary for robotics, machine perception & AR! Stay tuned for more breakthroughs at the intersection of AI, robotics, and DePIN. We're building the future of Physical AI and Spatial Computing at Over the Reality 🌐 What do you think, ready for robodogs in your world? Drop your thoughts! 🤖🌐

Over the Reality 🌐

359,717 Aufrufe • vor 10 Monaten

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.

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

249,708 Aufrufe • vor 3 Jahren

HunyuanWorld-Voyager is here and fully open-source! The world’s first ultra-long-range world model with native 3D reconstruction, redefining AI-driven spatial intelligence for VR, gaming, and simulations. ✅Direct 3D Output: Exports point cloud videos to 3D formats without tools like COLMAP, enabling instant 3D application use. ✅Innovative 3D Memory: Introduces a scalable world caching mechanism, ensuring geometric consistency across any camera trajectory. ✅Top-Ranked Performance: #1 on Stanford’s WorldScore, excelling in video generation and 3D reconstruction benchmarks.( Built on HunyuanWorld 1.0, Voyager blends video generation with 3D modeling, delivering camera-controlled, high-fidelity RGB-D sequences. Control scenes via keyboard or joystick for unmatched 3D consistency. Explore now: 🌐Project Page: 🔗GitHub: 🤗HuggingFace: 📝Technical Details:

HunyuanWorld-Voyager is here and fully open-source! The world’s first ultra-long-range world model with native 3D reconstruction, redefining AI-driven spatial intelligence for VR, gaming, and simulations. ✅Direct 3D Output: Exports point cloud videos to 3D formats without tools like COLMAP, enabling instant 3D application use. ✅Innovative 3D Memory: Introduces a scalable world caching mechanism, ensuring geometric consistency across any camera trajectory. ✅Top-Ranked Performance: #1 on Stanford’s WorldScore, excelling in video generation and 3D reconstruction benchmarks.( Built on HunyuanWorld 1.0, Voyager blends video generation with 3D modeling, delivering camera-controlled, high-fidelity RGB-D sequences. Control scenes via keyboard or joystick for unmatched 3D consistency. Explore now: 🌐Project Page: 🔗GitHub: 🤗HuggingFace: 📝Technical Details:

Tencent Hy

198,289 Aufrufe • vor 10 Monaten

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.

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

We’re open-sourcing HY-World 2.0, a multimodal world model that generates, reconstructs, and simulates interactive *3D worlds* from text, images, and videos. Outputs can be integrated into game engines and embodied simulation pipelines. Key highlights: 🔹 One-click world generation Turn text or image into interactive 3D worlds automatically. 🔹 Pipeline-ready 3D outputs Editable 3D worlds for Unity and Unreal Engine, with standard 3D exports including mesh, 3DGS, and point clouds. 🔹 Unified world model system One model family for world generation and reconstruction across synthetic and real-world scenes. 🔹 Interactive character mode Explore generated 3D worlds in real time with physics-aware movement and collision support. ✨ Apply for access: 🔗 GitHub: 🤗 Hugging Face: 📄 Technical Report:

We’re open-sourcing HY-World 2.0, a multimodal world model that generates, reconstructs, and simulates interactive 3D worlds from text, images, and videos. Outputs can be integrated into game engines and embodied simulation pipelines. Key highlights: 🔹 One-click world generation Turn text or image into interactive 3D worlds automatically. 🔹 Pipeline-ready 3D outputs Editable 3D worlds for Unity and Unreal Engine, with standard 3D exports including mesh, 3DGS, and point clouds. 🔹 Unified world model system One model family for world generation and reconstruction across synthetic and real-world scenes. 🔹 Interactive character mode Explore generated 3D worlds in real time with physics-aware movement and collision support. ✨ Apply for access: 🔗 GitHub: 🤗 Hugging Face: 📄 Technical Report:

Tencent Hy

370,989 Aufrufe • vor 3 Monaten

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.

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 11 Monaten

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.

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

Robots are gaining spatial awareness with Over the Reality. 🤖 Powered by the world’s largest 3D dataset, we enable robots to see, sense, and collaborate in real-world environments. This early test shows how a Unitree Go2 perceives its surroundings through OVER’s VPS — on the right, the real life robot; on the left, its real-time perception of the position inside one of OVER’s 3D maps. Robotic spatial awareness is here, living in 155,000+ mapped locations and expanding every day. One step closer to Physical AI. Stay tuned for our upcoming ROS 2 integration, unlocking a universal framework for robotic perception leveraging OVER's infrastructure!

Robots are gaining spatial awareness with Over the Reality. 🤖 Powered by the world’s largest 3D dataset, we enable robots to see, sense, and collaborate in real-world environments. This early test shows how a Unitree Go2 perceives its surroundings through OVER’s VPS — on the right, the real life robot; on the left, its real-time perception of the position inside one of OVER’s 3D maps. Robotic spatial awareness is here, living in 155,000+ mapped locations and expanding every day. One step closer to Physical AI. Stay tuned for our upcoming ROS 2 integration, unlocking a universal framework for robotic perception leveraging OVER's infrastructure!

Over the Reality 🌐

263,818 Aufrufe • vor 9 Monaten

Excited to share ESI-BENCH, a benchmark for Embodied Spatial Intelligence! Most spatial reasoning benchmarks assume an oracle observer: the agent is given the right image, view, or 3D scene. But in the real world, the observer is also an actor. To understand space, agents must decide where to look, how to move, and when to interact, to reveal what is hidden: occlusions, containment, contact, dynamics, and functionality. In many cases, the hard part is not perception itself, but choosing the right action to make informative perception possible. ESI-BENCH tests this perception-action loop. Agents receive an egocentric observation and a spatial question, then must actively gather evidence through perception, locomotion, and manipulationbefore answering. The benchmark spans 10 task categories, 29 subcategories, and 3,081 instances, built in BEHAVIOR-1K across realistic interactive scenes. 🌍Webpage: 💻Code & data: Thanks for collaborators: Jiageng, Han, Manling Li , Leonidas Guibas, Fei-Fei Li , Jiajun Wu , Yejin Choi

Excited to share ESI-BENCH, a benchmark for Embodied Spatial Intelligence! Most spatial reasoning benchmarks assume an oracle observer: the agent is given the right image, view, or 3D scene. But in the real world, the observer is also an actor. To understand space, agents must decide where to look, how to move, and when to interact, to reveal what is hidden: occlusions, containment, contact, dynamics, and functionality. In many cases, the hard part is not perception itself, but choosing the right action to make informative perception possible. ESI-BENCH tests this perception-action loop. Agents receive an egocentric observation and a spatial question, then must actively gather evidence through perception, locomotion, and manipulationbefore answering. The benchmark spans 10 task categories, 29 subcategories, and 3,081 instances, built in BEHAVIOR-1K across realistic interactive scenes. 🌍Webpage: 💻Code & data: Thanks for collaborators: Jiageng, Han, Manling Li , Leonidas Guibas, Fei-Fei Li , Jiajun Wu , Yejin Choi

Yining Hong

49,989 Aufrufe • vor 2 Monaten