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.

Lucida from ByteDance Cool project! It transforms indoor video into editable 3D scenes; reconstructs objects as simulation-ready assets - VLM-based object detection and referring descriptions. - good at pose alignment - high-fidelity real-to-sim digital twins. - multi-view masks, boxes, partial point clouds - Seed3D 2.0 for image-to-3D asset gen

Wildminder

12,100 subscribers

46,938 Aufrufe • vor 1 Monat •via X (Twitter)

Kunst Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von basedcapital

basedcapitalvor 1 Monat

can lucida infer object articulation, or does simulation-ready here mean reconstructed geometry and aligned poses?

Profilbild von Daniel Pineda

Daniel Pinedavor 1 Monat

video to editable 3D assets is exactly the loop I want. Seed3D 2.0 any good on messy indoor clips?

Profilbild von Mono

Monovor 1 Monat

slop

Profilbild von Fisher Museum of Art

Fisher Museum of Artvor 1 Monat

这太牛逼了

Profilbild von COSMOS

COSMOSvor 1 Monat

wf

Profilbild von AIVEED.IO

AIVEED.IOvor 1 Monat

Really promising real-to-sim pipeline - clearer demos of articulation/physics interaction would make the “simulation-ready” claim land harder.

Profilbild von Levi

Levivor 1 Monat

insane tech from bytedance

Profilbild von Max Liebscher

Max Liebschervor 1 Monat

Endless possibilities....

Profilbild von ishaan

ishaanvor 1 Monat

OSS?

Profilbild von AI Mastery Guide

AI Mastery Guidevor 1 Monat

Video to 3D scenes is next level

Profilbild von Nicolás Demaria

Nicolás Demariavor 1 Monat

This looks amazing! How much did it cost and how long did it take? And how performant is it? If I dropped the generated scene into an engine and have an NPC would the scene contain enough semantic information for the NPC to actually identify and interact with things?

Ähnliche Videos

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄

Hao Zhao

52,340 Aufrufe • vor 1 Monat

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

373,065 Aufrufe • vor 6 Monaten

Unreal Engine asset packs are about to be worthless. Tencent just shipped HY-World 2.0. You type one sentence. It outputs a real 3D scene with meshes, point clouds, and 3DGS that drags straight into your game engine. Renders in real time on a consumer GPU. Phone video in, digital twin out, one forward pass. The marketplace economy of selling 3D assets just had its Napster moment.

Unreal Engine asset packs are about to be worthless. Tencent just shipped HY-World 2.0. You type one sentence. It outputs a real 3D scene with meshes, point clouds, and 3DGS that drags straight into your game engine. Renders in real time on a consumer GPU. Phone video in, digital twin out, one forward pass. The marketplace economy of selling 3D assets just had its Napster moment.

Ihtesham Ali

45,956 Aufrufe • vor 5 Monaten

📢📢GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction📢📢 Reconstructing high-fidelity 3D scenes from sparse RGB input is hard. It needs a strong 3D prior! We reformulate multi-view scene reconstruction as conditional 3D generation over overlapping spatial chunks, lifting posed image features into a generative shape prior via 3D conditioning. As an example prior, we build on Trellis2, and train it such that its reconstruction is pixel aligned and matches from all views. GenRecon achieves unprecedented reconstruction quality from any sparse RGB input sequence, even from a phone capture. The reconstruction also includes PBR materials which facilitates relighting and virtual object insertion. Amazing work by Katharina Schmid, Nicolas von Lützow, Jozef, Angela Dai

📢📢GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction📢📢 Reconstructing high-fidelity 3D scenes from sparse RGB input is hard. It needs a strong 3D prior! We reformulate multi-view scene reconstruction as conditional 3D generation over overlapping spatial chunks, lifting posed image features into a generative shape prior via 3D conditioning. As an example prior, we build on Trellis2, and train it such that its reconstruction is pixel aligned and matches from all views. GenRecon achieves unprecedented reconstruction quality from any sparse RGB input sequence, even from a phone capture. The reconstruction also includes PBR materials which facilitates relighting and virtual object insertion. Amazing work by Katharina Schmid, Nicolas von Lützow, Jozef, Angela Dai

Matthias Niessner

18,420 Aufrufe • vor 4 Monaten

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.

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

27,354 Aufrufe • vor 2 Jahren

Hyper3D just launched WorldGen, and it takes 3D generation from single assets to full scenes. From one image, it builds a structured 3D scene where every important object is its own editable asset. You can move it, replace it, edit it, and interact with it. How it works: 1. Upload a scene image 2. WorldGen identifies the objects 3. Generate the full scene with Max Gen and walk around with WASD 4. Select any object and move, delete, replace, or regenerate it with Hyper3D Rodin 5. Click "Interactive" to see physical properties 6. Export to Blender, Unity, or UE It pairs Rodin's independent Mesh assets with 3D Gaussian Splatting for the environment, and predicts position, scale, collision, mass, and friction. Built for embodied AI training, film pre-viz with video models like Seedance 2.5, game dev, and XR. From DeemosTech, whose CAST research won a Best Paper Award at SIGGRAPH 2025. Try Hyper3D WorldGen: Get updates Hyper3D by Deemos: 14-day Free Trial Code: 35TLO1MS #Hyper3D #DeemosTech #Rodin #WorldGen #AI3D

Hyper3D just launched WorldGen, and it takes 3D generation from single assets to full scenes. From one image, it builds a structured 3D scene where every important object is its own editable asset. You can move it, replace it, edit it, and interact with it. How it works: 1. Upload a scene image 2. WorldGen identifies the objects 3. Generate the full scene with Max Gen and walk around with WASD 4. Select any object and move, delete, replace, or regenerate it with Hyper3D Rodin 5. Click "Interactive" to see physical properties 6. Export to Blender, Unity, or UE It pairs Rodin's independent Mesh assets with 3D Gaussian Splatting for the environment, and predicts position, scale, collision, mass, and friction. Built for embodied AI training, film pre-viz with video models like Seedance 2.5, game dev, and XR. From DeemosTech, whose CAST research won a Best Paper Award at SIGGRAPH 2025. Try Hyper3D WorldGen: Get updates Hyper3D by Deemos: 14-day Free Trial Code: 35TLO1MS #Hyper3D #DeemosTech #Rodin #WorldGen #AI3D

LX™

92,219 Aufrufe • vor 21 Tagen

ByteDance just announced MagicVideo-V2 Multi-Stage High-Aesthetic Video Generation paper page: The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness. It demonstrates superior performance over leading Text-to-Video systems such as Runway, Pika 1.0, Morph, Moon Valley and Stable Video Diffusion model via user evaluation at large scale

ByteDance just announced MagicVideo-V2 Multi-Stage High-Aesthetic Video Generation paper page: The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness. It demonstrates superior performance over leading Text-to-Video systems such as Runway, Pika 1.0, Morph, Moon Valley and Stable Video Diffusion model via user evaluation at large scale

AK

181,049 Aufrufe • vor 2 Jahren

How do you go from scanning a real-world space → using it in an app, workflow, or environment? Our product team walks through Scaniverse step-by-step, from capturing spaces to generating production-ready 3D assets and enabling precise, real-world positioning. In the first video, Senior Product Manager, Bec Maxworth, walks through your entry point into Scaniverse from signing up to getting started so you can start building high-fidelity 3D models in minutes. Dive into the full walkthrough here: #NianticSpatial #Scaniverse #Reconstruction #VPS #GeospatialAI #AI #PhysicalAI

How do you go from scanning a real-world space → using it in an app, workflow, or environment? Our product team walks through Scaniverse step-by-step, from capturing spaces to generating production-ready 3D assets and enabling precise, real-world positioning. In the first video, Senior Product Manager, Bec Maxworth, walks through your entry point into Scaniverse from signing up to getting started so you can start building high-fidelity 3D models in minutes. Dive into the full walkthrough here: #NianticSpatial #Scaniverse #Reconstruction #VPS #GeospatialAI #AI #PhysicalAI

Niantic Spatial 🌎

10,739 Aufrufe • vor 6 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

One of the coolest 3d real estate demos I've seen in a while. Treedis brings together gaussian splats for area understanding → BIM data to check which units are available → Matterport for indoor views → and image editing AI to restyle decor and see different times of day. The data conflation problem of wrangling all these mismatched 3D assets into one seamless view is hard to do automatically - but this experience shows why it's worth solving. Every digital twin and AR vision video promises this, but here's someone actually building it.

One of the coolest 3d real estate demos I've seen in a while. Treedis brings together gaussian splats for area understanding → BIM data to check which units are available → Matterport for indoor views → and image editing AI to restyle decor and see different times of day. The data conflation problem of wrangling all these mismatched 3D assets into one seamless view is hard to do automatically - but this experience shows why it's worth solving. Every digital twin and AR vision video promises this, but here's someone actually building it.

Bilawal Sidhu

38,691 Aufrufe • vor 11 Monaten

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors paper page: Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space, either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors, these methods often lead to geometric anomalies and multi-view inconsistency. Recently, researchers have attempted to improve the genuineness of 3D objects by directly training on 3D datasets, albeit at the cost of low-quality texture generation due to the limited texture diversity in 3D datasets. To harness the advantages of both approaches, we propose Bidirectional Diffusion(BiDiff), a unified framework that incorporates both a 3D and a 2D diffusion process, to preserve both 3D fidelity and 2D texture richness, respectively. Moreover, as a simple combination may yield inconsistent generation results, we further bridge them with novel bidirectional guidance. In addition, our method can be used as an initialization of optimization-based models to further improve the quality of 3D model and efficiency of optimization, reducing the generation process from 3.4 hours to 20 minutes. Experimental results have shown that our model achieves high-quality, diverse, and scalable 3D generation.

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors paper page: Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space, either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors, these methods often lead to geometric anomalies and multi-view inconsistency. Recently, researchers have attempted to improve the genuineness of 3D objects by directly training on 3D datasets, albeit at the cost of low-quality texture generation due to the limited texture diversity in 3D datasets. To harness the advantages of both approaches, we propose Bidirectional Diffusion(BiDiff), a unified framework that incorporates both a 3D and a 2D diffusion process, to preserve both 3D fidelity and 2D texture richness, respectively. Moreover, as a simple combination may yield inconsistent generation results, we further bridge them with novel bidirectional guidance. In addition, our method can be used as an initialization of optimization-based models to further improve the quality of 3D model and efficiency of optimization, reducing the generation process from 3.4 hours to 20 minutes. Experimental results have shown that our model achieves high-quality, diverse, and scalable 3D generation.

AK

38,853 Aufrufe • vor 2 Jahren

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein

Matthias Niessner

18,903 Aufrufe • vor 11 Monaten

is it legal? NVIDIA and Microsoft just open-sourced the pieces of a full 3D studio for Opus 5.5 15 github repos, sorted by what you want to make: GENERATE 3D ASSETS 01. TRELLIS.2 by Microsoft: -> one image in, a fully textured 3D asset out, about 3 seconds on an H100 02. Hunyuan3D-2.1 by Tencent: -> production-ready 3D assets with PBR textures 03. stable-fast-3d by Stability AI: -> one photo to a clean UV-unwrapped mesh, built for speed 04. meshy-mcp-server by Meshy: -> text or image to 3D, then remesh, retexture, rig and animate from your agent BUILD SCENES AND WORLDS 05. mcp-for-blender: -> prompt-driven modeling, scene building and edits in a live Blender 06. HY-World-2.0 by Tencent: -> text or a single image to a navigable 3D world 07. supersplat by PlayCanvas: -> inspect, edit, optimize and publish 3D Gaussian splats in the browser 08. kit-usd-agents by NVIDIA: -> edit Omniverse USD scenes in plain English, plus MCP servers for Kit and Isaac Sim MAKE A GAME 09. unity-mcp: -> run the Unity Editor in plain English: scenes, C# scripts, assets, tests, builds 10. godot-ai: -> 46 tools for a live Godot editor: scenes, scripts, signals, UI, particles 11. unreal-engine-mcp: -> drive a live Unreal Editor: actors, world building, Blueprints 3D ON THE WEB 12. editor-mcp-server by PlayCanvas: -> your agent builds PlayCanvas scenes and checks they actually run 13. three.js: -> the JavaScript 3D library itself, 115k stars on GitHub 14. react-three-fiber: -> build three.js scenes as reusable React components 15. threejs-skills: -> 10 three.js skills for Claude Code, from shaders to post-processing a full 3D pipeline, and every piece of it lives on github

is it legal? NVIDIA and Microsoft just open-sourced the pieces of a full 3D studio for Opus 5.5 15 github repos, sorted by what you want to make: GENERATE 3D ASSETS 01. TRELLIS.2 by Microsoft: -> one image in, a fully textured 3D asset out, about 3 seconds on an H100 02. Hunyuan3D-2.1 by Tencent: -> production-ready 3D assets with PBR textures 03. stable-fast-3d by Stability AI: -> one photo to a clean UV-unwrapped mesh, built for speed 04. meshy-mcp-server by Meshy: -> text or image to 3D, then remesh, retexture, rig and animate from your agent BUILD SCENES AND WORLDS 05. mcp-for-blender: -> prompt-driven modeling, scene building and edits in a live Blender 06. HY-World-2.0 by Tencent: -> text or a single image to a navigable 3D world 07. supersplat by PlayCanvas: -> inspect, edit, optimize and publish 3D Gaussian splats in the browser 08. kit-usd-agents by NVIDIA: -> edit Omniverse USD scenes in plain English, plus MCP servers for Kit and Isaac Sim MAKE A GAME 09. unity-mcp: -> run the Unity Editor in plain English: scenes, C# scripts, assets, tests, builds 10. godot-ai: -> 46 tools for a live Godot editor: scenes, scripts, signals, UI, particles 11. unreal-engine-mcp: -> drive a live Unreal Editor: actors, world building, Blueprints 3D ON THE WEB 12. editor-mcp-server by PlayCanvas: -> your agent builds PlayCanvas scenes and checks they actually run 13. three.js: -> the JavaScript 3D library itself, 115k stars on GitHub 14. react-three-fiber: -> build three.js scenes as reusable React components 15. threejs-skills: -> 10 three.js skills for Claude Code, from shaders to post-processing a full 3D pipeline, and every piece of it lives on github

Mnimiy

205,109 Aufrufe • vor 7 Tagen

Introducing ✨RigidFormer: Learning Rigid Dynamics with Transformers - our attempt to scale learning-based physical dynamics with Transformers. RigidFormer learns rigid dynamics with Transformers. It is a mesh-free, object-centric Transformer for multi-object rigid-body contact dynamics from point clouds. Learning physics with purely neural simulators, without relying on traditional physics engines, is an important and widely studied problem. Prior SOTA methods often use graph neural networks for accuracy and generalization, but still struggle with efficient, high-fidelity simulation at scale. RigidFormer uses only point inputs, matches or outperforms mesh-based baselines on standard benchmarks, runs much faster, generalizes across point resolutions and datasets, and scales to 200+ objects. We also show a preliminary extension to command-conditioned articulated bodies by treating body parts as interacting object-level components. RigidFormer is mesh-free: it does not require mesh connectivity, SDFs, or vertex-level message passing, making it well-suited for point-cloud observations and scalable simulation. This architecture can also be adapted to learn soft-body dynamics by replacing the rigid-body module (differentiable Kabsch alignment). 🎬See our video for more details. Many thanks to my amazing collaborators: Minghao Guo Minghao Guo, Haixu Wu Haixu Wu 吴海旭, Doug Roble, Tuur Stuyck Tuur Stuyck, and Wojciech Matusik Wojciech Matusik. Project page: Paper:

Introducing ✨RigidFormer: Learning Rigid Dynamics with Transformers - our attempt to scale learning-based physical dynamics with Transformers. RigidFormer learns rigid dynamics with Transformers. It is a mesh-free, object-centric Transformer for multi-object rigid-body contact dynamics from point clouds. Learning physics with purely neural simulators, without relying on traditional physics engines, is an important and widely studied problem. Prior SOTA methods often use graph neural networks for accuracy and generalization, but still struggle with efficient, high-fidelity simulation at scale. RigidFormer uses only point inputs, matches or outperforms mesh-based baselines on standard benchmarks, runs much faster, generalizes across point resolutions and datasets, and scales to 200+ objects. We also show a preliminary extension to command-conditioned articulated bodies by treating body parts as interacting object-level components. RigidFormer is mesh-free: it does not require mesh connectivity, SDFs, or vertex-level message passing, making it well-suited for point-cloud observations and scalable simulation. This architecture can also be adapted to learn soft-body dynamics by replacing the rigid-body module (differentiable Kabsch alignment). 🎬See our video for more details. Many thanks to my amazing collaborators: Minghao Guo Minghao Guo, Haixu Wu Haixu Wu 吴海旭, Doug Roble, Tuur Stuyck Tuur Stuyck, and Wojciech Matusik Wojciech Matusik. Project page: Paper:

Zhiyang (Frank) Dou

582,022 Aufrufe • vor 5 Monaten

Another city. Another full 3D Gaussian Splat reconstruction. This entire neighborhood was captured while walking with an Insta360 X5, then processed with our GPU pipeline and transformed into a high-fidelity, machine-readable 3D environment with Over the Reality. What you’re seeing is not an isolated virtual world. It’s a 3D digital twin of a real-world location, built from structured spatial data where every building, street, and detail can become usable by AI, robotics, and XR. And it’s happening at scale, across cities in more than 180 countries every day. Have an Insta360 X5 and want to become a mapper? Apply here: Want to build a 3D Gaussian Splat from a video you already recorded? Do it for free at powered by Over the Reality.

Another city. Another full 3D Gaussian Splat reconstruction. This entire neighborhood was captured while walking with an Insta360 X5, then processed with our GPU pipeline and transformed into a high-fidelity, machine-readable 3D environment with Over the Reality. What you’re seeing is not an isolated virtual world. It’s a 3D digital twin of a real-world location, built from structured spatial data where every building, street, and detail can become usable by AI, robotics, and XR. And it’s happening at scale, across cities in more than 180 countries every day. Have an Insta360 X5 and want to become a mapper? Apply here: Want to build a 3D Gaussian Splat from a video you already recorded? Do it for free at powered by Over the Reality.

Over the Reality 🌐

400,303 Aufrufe • vor 5 Monaten

TEDRA Text-based Editing of Dynamic and Photoreal Actors discuss: Over the past years, significant progress has been made in creating photorealistic and drivable 3D avatars solely from videos of real humans. However, a core remaining challenge is the fine-grained and user-friendly editing of clothing styles by means of textual descriptions. To this end, we present TEDRA, the first method allowing text-based edits of an avatar, which maintains the avatar's high fidelity, space-time coherency, as well as dynamics, and enables skeletal pose and view control. We begin by training a model to create a controllable and high-fidelity digital replica of the real actor. Next, we personalize a pretrained generative diffusion model by fine-tuning it on various frames of the real character captured from different camera angles, ensuring the digital representation faithfully captures the dynamics and movements of the real person. This two-stage process lays the foundation for our approach to dynamic human avatar editing. Utilizing this personalized diffusion model, we modify the dynamic avatar based on a provided text prompt using our Personalized Normal Aligned Score Distillation Sampling (PNA-SDS) within a model-based guidance framework. Additionally, we propose a time step annealing strategy to ensure high-quality edits. Our results demonstrate a clear improvement over prior work in functionality and visual quality.

AK

17,302 Aufrufe • vor 2 Jahren

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360°, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360° head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data 🏠 🌍 🎥 Great work by Tobias Kirschstein and Simon Giebenhain!

Matthias Niessner

96,371 Aufrufe • vor 10 Monaten