Mixamo 3D characters with skeleton for animation
Set of 95 3D character models in T-pose with bones and textures for 3D animation tasks.
Hugging Face datasets with plain-language descriptions: what's inside and what models to train on them. 4,788 in the catalog so far, with new ones added every hour.
Answered by Gemini 4 · the chat is kept only in this tab
Set of 95 3D character models in T-pose with bones and textures for 3D animation tasks.
Over 2,000 CMU motion capture animation clips in GLB format with skeletons and characters.
Fewer than a thousand 3D models of diverse professionals and animals with a unified skeleton and facial animation.
CAD assets and scenes with configured physics for home robot simulation.
1,000 interior 3D scenes in USDZ format for simulation and robotics in NVIDIA Isaac Sim.
Optimized 3D models of NASA spacecraft, rovers, and spacesuits for engines and the web.
107 noisy 3D point clouds reconstructed from regular RGB video, with room layout annotations.
49,662 real mechanical engineering samples in four formats: PDF drawing, PNG image, STEP 3D model, and CadQuery code.
Complete collection of maps, seasonal landscapes, and game scenes from Dota 2 with meshes, materials, and textures.
A collection of optimized 3D models of museum artifacts for 3D generation, gaming, and computer vision.
A unified metadata table for searching and selecting 3D models by size, style, and characteristics.
A massive collection of millions of RGB images and depth maps totaling 2.71 TB for training 3D vision and robotics.
A collection of code-generated open 3D worlds with metadata in English and Chinese.
3D simulation asset of the Asimov 1 humanoid robot in USD format.
Curated 3D scenes with prompts, reasoning, and HTML/JavaScript code for generating 3D graphics.
A task suite for evaluating AI agents' ability to modify 3D Blender scenes via code based on visual differences.
18.8 hours of 3D locomotion animations (100STYLE) on a skeleton and ready-made character for motion generation.
30 detailed 3D living space scenes featuring annotations for over 13,000 objects for Embodied AI.
1 million to 10 million rendered videos and metadata of 3D/4D models for text-to-3D and image-to-3D tasks.
A set of 326 motion files in GLB format based on the Microsoft Rocketbox avatar library.
Simulation-ready OpenUSD models of lab tables, instruments, and reagent containers.
Collection of 1,030 Google 3D object scans with textures and meshes.
High-precision aerodynamic simulation dataset for training physics AI models in automotive engineering.
143 optical parkour motion capture clips with 3D obstacle geometry for training humanoid robots.