Skip to content

Hongyang-Du/awesome-3d-datasets

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

80 Commits
.github/workflows
.github/workflows
 
 
images
images
 
 
README.md
README.md
 
 

Repository files navigation

Awesome 3d Datasets

Last updated: 2026-03-27

awesome-3d-datasets

🌟 Overview

📄 Citation

Coming soon

⚒️ Applications

🔄 3D Reconstruct

Title Year Paper Website Code HuggingFace
DUSt3R: Geometric 3D Vision Made Easy 2024 📄 Paper 🌍 Website 💾 Code -
VGGT: Visual Geometry Grounded Transformer 2025 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
$\pi^3$: Scalable Permutation-Equivariant Visual Geometry Learning 2025 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds 2024 📄 Paper 🌍 Website 💾 Code -
MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details 2025 📄 Paper - - -
MASt3R: Grounding Image Matching in 3D 2024 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
Mickey: Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences 2024 📄 Paper 🌍 Website 💾 Code -
StreamVGGT: Streaming 4D Visual Geometry Transformer 2025 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second 2025 📄 Paper 🌍 Website 💾 Code -
TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction 2025 📄 Paper - 💾 Code -
STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer 2025 📄 Paper 🌍 Website 💾 Code -
Depth Anything 3: Recovering the Visual Space from Any Views 2025 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
RayZer: A Self-supervised Large View Synthesis Model 2025 📄 Paper 🌍 Website 💾 Code -

✨ 3D Generation

Title Year Paper Website Code HuggingFace
DreamFusion: Text-to-3D using 2D Diffusion 2022 📄 Paper 🌍 Website - -
Magic3D: High-Resolution Text-to-3D Content Creation 2023 📄 Paper 🌍 Website - -
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation 2024 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D Generation 2025 📄 Paper 🌍 Website - -
Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data 2025 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
MVDream: Multi-view Diffusion for 3D Generation 2024 📄 Paper 🌍 Website 💾 Code -
Structured 3D Latents for Scalable and Versatile 3D Generation 2025 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation 2024 📄 Paper - - -
AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer 2026 📄 Paper - 💾 Code -

🎬 Video Generation

Title Year Paper Website Code HuggingFace
CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer 2024 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
Wan: Open and Advanced Large-Scale Video Generative Models 2025 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
Lumiere: A Space-Time Diffusion Model for Video Generation 2024 📄 Paper 🌍 Website 💾 Code -
Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning 2024 📄 Paper 🌍 Website - -
Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets 2023 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
3D-Aware Video Generation 2023 📄 Paper 🌍 Website 💾 Code -
World-consistent Video Diffusion with Explicit 3D Modeling 2024 📄 Paper 🌍 Website - -
IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular Videos 2025 📄 Paper 🌍 Website - -
Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling 2025 📄 Paper 🌍 Website - -
Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals 2025 📄 Paper 🌍 Website 💾 Code -
PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation 2024 📄 Paper 🌍 Website 💾 Code -
Tora: Trajectory-oriented Diffusion Transformer for Video Generation 2025 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
CamI2V: Camera-Controlled Image-to-Video Diffusion Model 2024 📄 Paper 🌍 Website 💾 Code 😊 HuggingFace
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer 2026 📄 Paper 🌍 Website 💾 Code -
daVinci-MagiHuman: A Single-Stream Architecture for Fast Audio-Video Foundation Model 2026 📄 Paper - 💾 Code 😊 HuggingFace

🌐 World Models

Title Year Paper Website Code HuggingFace
Learning to Simulate Complex Physics with Graph Networks 2020 📄 Paper 🌍 Website 💾 Code -
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids 2019 📄 Paper 🌍 Website 💾 Code -
Learning Mesh-Based Simulation with Graph Networks 2021 📄 Paper 🌍 Website 💾 Code -
SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation 2021 📄 Paper 🌍 Website 💾 Code -
3D Gaussian Splatting for Real-Time Radiance Field Rendering 2023 📄 Paper 🌍 Website 💾 Code -
Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis 2023 📄 Paper 🌍 Website 💾 Code -
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering 2024 📄 Paper 🌍 Website 💾 Code -
Gaussian Splatting SLAM 2024 📄 Paper 🌍 Website 💾 Code -
Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians 2024 📄 Paper - 💾 Code -
ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation 2025 📄 Paper 🌍 Website - -
RoboScape: Physics-informed Embodied World Model 2025 📄 Paper - 💾 Code -
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics 2025 📄 Paper - 💾 Code
World-in-World: World Models in a Closed-Loop World 2026 📄 Paper - 💾 Code -
FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction 2026 📄 Paper - 💾 Code 😊 HuggingFace
Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling 2026 📄 Paper 🌍 Website 💾 Code -

📚 3D Datasets Summary

3dv.001

👤 Human

Dataset Year Granularity Tasks Size Site Description
SAM 3D 2026 Human Body Full-Body Human Mesh Recovery 5M Github A dataset released by Meta (2025) designed for single-image full-body reconstruction. It adapts the "Segment Anything" philosophy to the 3D human recovery domain.
InterAct 2025 Human Body 3D Motion Generation 1.1K Github A comprehensive dataset for Human-Human and Human-Object Interaction. It focuses on "social" 3D understanding, ensuring that physical contacts (e.g., a handshake or sitting on a chair) are mathematically accurate.
GigaHands 2025 Human Hand 3D bimanual hand 14K Github A large dataset of bimanual hand–object interactions with 183 million frames, dense annotations (per hand & object), and 51 camera views for motion clips.
EgoHumans 2023 Human Body 3D Multi-Human Tracking, 3D Pose Estimation 125K Github A specialized 3D benchmark designed to address the limitations of traditional egocentric datasets, which typically focus on a single subject in indoor settings.
EgoExo4D 2023 Human Body Ego-Exo Relation, Ego-Exo Translation, 3D Pose Estimation 1.4K Github A massive-scale, multimodal, and multiview video dataset specifically designed to bridge the gap between first-person (egocentric) and third-person (exocentric) perspectives.
H3WB 2022 Human Body 3D Pose Estimation 100K Github H3WB augments Human3.6M with 133 whole-body 3D keypoint annotations (body, hands, face, feet) for 100k images via a multi-view annotation pipeline.
FaceScape 2020 Human Face Classification, Segmentation, Reconstruction, Completion, Recognition 18K Github 18,760 high-quality textured 3D face meshes from 938 people with pore-level geometry, uniform topology base meshes + displacement maps, and 20 expressions per subject

🎯 Object

Dataset Year Granularity Tasks Size Site Description
uCO3D 2025 Object Few-shot 3D Reconstruction 1K Github uCO3D is the largest publicly-available collection of high-resolution videos of objects with 3D annotations that ensures full-360 degree coverage.
HPSketch 2025 Object - 151.9K Github A history-based parametric CAD sketch dataset with advanced engineering commands; includes 151,984 sketches, 377,623 loops, and 29 command types for learning sketch histories and operations.
CBF 2025 Object - 20K Github 20,000 CAD B-rep models composed of a base plate plus three geometric features each, with per-face labels stored in JSON; released with BRepFormer to benchmark complex geometric feature recognition on B-reps.
Parametric 20000 2024 Object - 20K Link Multi-modal CAD shapes: each instance includes a point cloud, a triangle mesh, and a B-Rep file.
WildRGB-D 2024 Object View Synthesis, Pose Estimation, 6D Object Tracking, 3D Reconstruction 8.5K Github A large-scale real-world RGB-D object video collection (~20K videos, 8.5K objects) with 360° views, diverse backgrounds, object masks, real-scale camera poses, and aggregated point clouds.
BRep2Seq 2024 Object - 1M Link Introduces a synthetic CAD dataset (~1,000,000 models) of B-rep solids paired with feature-based construction sequences, and a hierarchical Transformer (Brep2Seq) for reconstructing/generating editable CAD models.
Objaverse 2023 Object 3D Asset Collection, Annotation, Multimodal Learning 800K Github 800K+ free 3D object models with rich metadata (captions, tags, categories) and some objects include animations.
DIVA-360 2023 Object Novel View Synthesis, NeRF Pretraining 50 Github High-resolution synchronized multi-view video of dynamic table-scale scenes (53 RGB cameras), including hand-object interactions, segmentation masks, audio, and text descriptions.
StrobeNet 2021 Object 3D Reconstruction 120K Link Articulated-object categories providing many rendered RGB views plus joint + part segmentation and ground truth implicit / point cloud geometry to support animatable 3D reconstructions from sparse unposed images.
Amazon Berkeley Objects 2021 Object 3D Reconstruction, Multi-view Retrieval, Material Estimation 8K Website A large dataset of real household objects with high-resolution CAD models, PBR materials, real product images & metadata, enabling single-view 3D reconstruction, material estimation, & multi-view retrieval.
Fusion 360 Gallery Dataset 2021 Object 3D reconstruction, segmentation, assembly prediction, sequential modeling 8K Github A parametric CAD dataset from real user submissions (≈20,000 designs) offering “sketch & extrude” construction sequences, operation-based face segmentation, and multi-part assemblies with joint and connectivity info.
CO3Dv2 2021 Object Novel View Synthesis, Category-level 3D Reconstruction 19K Github A large-scale real-object dataset with object-centric multi-view images, annotated camera poses, and ground-truth 3D point clouds across 50 object categories.
3D-FUTURE 2020 Object Navigation, Exploration, Interaction 10K Github A furniture CAD + texture dataset with nearly 10,000 detailed instances used in realistic room scenes, offering aligned textures for object pose, segmentation, and shape retrieval tasks.
SketchGraphs 2020 Object - 15M Github A large-scale dataset of ~15M 2D parametric CAD sketches represented as geometric-constraint graphs to support generative modeling of sketches and prediction of likely constraints.
ABC 2019 Object Shape Analysis, Segmentation, Surface Fitting 1M Link A huge collection of CAD models with analytic parametric curves & surfaces, sharp feature annotations, patch decompositions, and ground truth differential geometry.
ScanObjectNN 2019 Object 700 Link Real-world indoor object point clouds (with background clutter, occlusion, partial scans) from SceneNN & ScanNet, over 15 categories.
Thingi10K 2016 Object Scene Understanding, Semantic Segmentation, Layout Prediction 300 Github A collection of 10,000 real-world 3D printing meshes from Thingiverse, across 72 categories, with geometric issues like non-manifoldness and self-intersections included.
A Large Dataset of Object Scans 2016 Object Object Scanning, 3D Reconstruction, Object Categorization 10K Github A public domain dataset of 10,000+ consumer-grade real-object 3D scans, diverse in category and size.
ShapeNet 2015 Object Single-view Reconstruction, Multi-view Reconstruction 300M Link 3D CAD models (≈3M shapes), including ~220K models with classifications, part annotations, symmetry planes, alignments, physical size info.

🏙️ Scene

Dataset Year Granularity Tasks Size Site Description
SceneSplat++ 2025 Mixed 3D Scene Captioning, Open-Vocabulary 3D Segmentation, 3D Visual Grounding 48K Hugging
Face		 Currently the world’s largest open-source 3D scene dataset. It bridges the gap between vision and language by enriching thousands of reconstructed scenes with semantic language features.
InteriorGS 2025 Scene
Indoor		 3D scene understanding, controllable scene generation, embodied agent navigation 100K Hugging
Face		 A synthetic dataset with 100K procedurally generated indoor scenes, realistic object placement, simulated Aria-glass camera, full 6DoF trajectories, 3D floor-plans, 2D instance segmentation, and depth (range maps).
Aria Synthetic Environments 2023 Scene
Indoor		 3D Question Answering, Spatial Reasoning, Scene Understanding 100K Link A synthetic dataset with 100K procedurally generated indoor scenes, realistic object placement, simulated Aria-glass camera, full 6DoF trajectories, 3D floor-plans, 2D instance segmentation, and depth (range maps).
DL3DV-10K 2023 Scene Novel View Synthesis, NeRF Pretraining 10K Website A large real-world multi-view video dataset capturing 10,510 4K videos across 65 kinds of POI scenes, annotated for complexity (reflection, transparency, lighting, texture) to support generalizable novel view synthesis and NeRF research.
Aria Digital Twin 2023 Scene
Indoor		 3D Question Answering, Spatial Reasoning, Scene Understanding 400 Link An egocentric dataset captured with wearable glasses, offering synchronized RGB + monocrome cameras, IMU, full sensor calibration, depth maps, 6-DoF poses (device & object), human pose & eye gaze, segmentation & synthetic renderings.
PointOdyssey 2023 Scene 3D Generation, Multimodal Learning, Simulation 104 Link A synthetic dataset with natural motion, deformable characters, diverse scenes & materials, and long videos for fine-grained point-tracking evaluation.
ScanNet++ 2023 Scene
Indoor		 1K Website A high-fidelity indoor scene dataset with sub-mm laser scans, high-res DSLR + iPhone RGB-D captures, dense mesh & semantic + instance annotations, supporting novel view synthesis & scene understanding.
Kubric 2022 Mixed Semantic Mapping, 2.5D Reconstruction, View-consistent Semantics N/A Github Kubric is a framework for generating photo-realistic synthetic scenes in Python (via Blender + PyBullet), with rich annotations (depth, segmentation, bounding boxes, camera pose, optical flow, etc.), scalable to TBs of data.
HM3D 2021 Scene
Indoor		 1K High-fidelity set of 1,000 real-world indoor 3D meshes with extensive navigable space, clean reconstructions, and textured geometry.
HyperSim 2021 Scene
Indoor		 Multi-task Scene Understanding 461 Github A photorealistic synthetic indoor dataset with full scene geometry + materials + lighting, dense per-pixel semantic + instance segmentation, and detailed lighting decomposition.
Habitat 2.0 2021 Scene
Indoor		 Pick, Place, Navigate, Open, Close, Rearrange 111 Link A reconfigurable, artist-authored indoor dataset of apartments with articulated objects, semantic class and surface annotations, collision proxies, matching real layout footprints.
Virtual KITTI2 2020 Scene
Outdoor		 6D Pose Estimation, Object Detection, Benchmarking 5 Link Virtual KITTI is a synthetic driving-scene dataset with fully annotated RGB, depth, optical flow, semantic & instance segmentation, and variants in weather/camera conditions using cloned sequences from KITTI.
RELLIS-3D 2020 Scene
Outdoor		 3D Semantic Segmentation, Sensor Fusion, Autonomous Navigation 13K Website A multimodal off-road robotics dataset with 13,556 LiDAR scans, 6,235 RGB images, point-wise & pixel-wise semantic labels over 20 classes, plus stereo, GPS/IMU, and camera-LiDAR calibrated data.
3D-FRONT 2020 Scene
Indoor		 Scene Understanding, Layout Analysis, Object Arrangement 18K HuggingFace Synthetic indoor scene dataset with professionally designed layouts, high-quality textured furniture models, consistent style curation, and semantic annotations.
Structured3D 2020 Scene
Indoor		 Reconstruction, Segmentation, Object Detection 3.5K Link Structured3D provides synthetic photo-realistic indoor scenes with rich “primitive + relationship” structure annotations (planes, lines, junctions, room layouts, floorplans), plus depth maps, semantic masks, and varied lighting / furnishing configurations.
Mapillary 2020 Scene
Outdoor		 Reconstruction, Semantics, Viewpoint Estimation 1.6M Link A large street-level image sequence dataset with 1.6M geo-tagged images, covering diverse cities, seasons, weather, and appearance changes for lifelong place recognition.
BlendedMVS 2019 Scene Reconstruction, Alignment, Evaluation 113 Github Multi-view stereo, offering 113 textured mesh scenes, rendered + blended image inputs, and ground-truth depth maps to improve generalization.
Replica 2019 Scene
Indoor		 Scene Graph Generation, Object Detection, Relationship Modeling 18 Github 18 photo-realistic indoor scenes with dense meshes, HDR textures, semantic & instance annotations, plus mirror and glass reflectors.
RealEstate10K 2018 Scene Part Segmentation, Hierarchical Labeling, Shape Understanding 10K Link Camera trajectories from ~10,000 YouTube real-estate videos, with pose + intrinsics data for 10 million frames over ~80,000 clips.
MegaDepth 2018 Scene Multisensory Perception, Object Interaction, Representation Learning 200 Link Diverse scene-depth dataset built from Internet multi-view photo collections, offering ~130K images with dense depth / ordinal depth labels from ~200 reconstructed scenes.
DeepMVS 2018 Scene CAD Alignment, 3D Matching, Pose Estimation 120 Link A photorealistic synthetic multi-view dataset (MVS-SYNTH: 120 urban sequences, 100 frames each, with ground truth disparities + full camera calibration) plus real indoor/outdoor image sets, for training disparity prediction in MVS.
ScanNet 2017 Scene
Indoor		 Feature Matching, Registration, 3D Reconstruction 1.5K Link An indoor RGB-D scene dataset with 1,513 scans across 707 spaces, ~2.5 million frames, dense surface reconstructions, semantic + instance labels, and aligned CAD models.
Matterport3D 2017 Scene
Indoor		 90 Website Indoor RGB-D dataset with 90 scenes, 194,400 RGB-D images, textured meshes and semantic/instance annotations.
Semantic3D 2016 Scene
Outdoor		 Point Cloud Classification, Semantic Segmentation 30 Link An outdoor laser-scanned benchmark of ~30 high-density static scans (≈4 B points), with manual semantic labels across 8 classes.
SceneNN / ObjectNN 2016 Scene
Indoor		 Multi-view Fusion, 3D Reconstruction, Semantic Segmentation 100 Link An indoor RGB-D scene dataset with ≈100 reconstructed scenes into triangle meshes; per-vertex, per-pixel semantic and instance annotations; also provides bounding boxes (axis-aligned & oriented) and object poses.
Virtual KITTI2 2016 Scene
Outdoor		 35 Link A photo-realistic synthetic video dataset cloned from KITTI, with automatic ground truth for object detection/tracking, scene & instance segmentation, depth, optical flow, and with weather & camera-angle variants.

📊 Modalities of 3D datasets

✅ indicates supported modality, * indicates CAD mesh

📝 Modality includes available signals like RGB, Depth, Pose, Segmentation, Flow, Mesh, Action...

Dataset RGB-D Point Cloud Mesh Multi-view Voxel Implicit Field
GigaHands ❌ ❌ ✅ ✅ ❌ ❌
InteriorGS ✅ ❌ ❌ ✅ ❌ ❌
HPSketch ❌ ❌ ❌ ❌ ❌ ❌
CBF ❌ ❌ ❌ ❌ ❌ ❌
Parametric 20000 ❌ ✅ ✅* ❌ ❌ ❌
WildRGB-D ✅ ✅ ❌ ✅ ❌ ❌
BRep2seq ❌ ❌ ✅* ❌ ❌ ❌
Aria Synthetic Environments ✅ ❌ ❌ ❌ ❌ ❌
DL3DV-10K ❌ ❌ ❌ ✅ ❌ ❌
PointOdyssey ❌ ❌ ✅ ✅ ❌ ❌
Aria Digital Twin ✅ ❌ ❌ ✅ ❌ ❌
ScanNet++ ✅ ✅ ✅ ✅ ❌ ❌
Objaverse ❌ ❌ ✅ ❌ ❌ ❌
DIVA-360 ❌ ❌ ❌ ✅ ❌ ❌
H3WB ❌ ❌ ❌ ✅ ❌ ❌
Kubric ✅ ✅ ✅ ✅ ❌ ❌
Amazon Berkeley Objects ❌ ❌ ✅* ✅ ❌ ❌
HM3D ❌ ❌ ✅ ❌ ❌ ❌
Fusion 360 Gallery Dataset ❌ ❌ ✅* ❌ ❌ ❌
CO3Dv2 ❌ ✅ ❌ ✅ ❌ ❌
HyperSim ✅ ❌ ❌ ✅ ❌ ❌
Habitat 2.0 ❌ ❌ ✅ ❌ ❌ ❌
StrobeNet ❌ ✅ ❌ ✅ ❌ ✅
Virtual KITTI 2 ✅ ❌ ❌ ❌ ❌ ❌
RELLIS-3D ❌ ✅ ❌ ❌ ❌ ❌
FaceScape ❌ ❌ ✅ ✅ ❌ ❌
A Large Dataset of Object Scans ✅ ✅ ❌ ❌ ❌ ❌
3D-FRONT ❌ ❌ ✅* ❌ ❌ ❌
3D-FUTURE ❌ ❌ ✅* ❌ ❌ ❌
SketchGraphs ❌ ❌ ❌ ❌ ❌ ❌
Structured3D ✅ ❌ ✅ ✅ ❌ ❌
Mapillary ❌ ❌ ❌ ✅ ❌ ❌
ScanObjectNN ❌ ✅ ❌ ❌ ❌ ❌
ABC ❌ ❌ ✅* ❌ ✅ ❌
BlendedMVS ✅ ❌ ✅ ✅ ❌ ❌
Replica ❌ ❌ ✅ ❌ ❌ ❌
RealEstate10K ❌ ❌ ❌ ✅ ❌ ❌
MegaDepth ✅ ❌ ❌ ✅ ❌ ❌
DeepMVS ✅ ❌ ❌ ❌ ❌ ❌
ScanNet ✅ ✅ ✅ ✅ ❌ ❌
Matterport3D ✅ ❌ ✅ ❌ ❌ ❌
Thingi10K ❌ ❌ ✅* ❌ ✅ ❌
Semantic3D ❌ ✅ ❌ ❌ ❌ ❌
SceneNN / ObjectNN ✅ ✅ ✅ ✅ ❌ ❌
A Large Dataset of Object Scans ❌ ✅ ✅ ❌ ❌ ❌
Virtual KITTI ✅ ❌ ❌ ❌ ❌ ❌
ShapeNet ❌ ❌ ✅* ❌ ✅ ❌
InterAct ❌ ❌ ✅* ❌ ❌ ❌
uCO3D ❌ ✅ ❌ ✅ ❌ ❌
SceneSplat++ ✅ ✅ ❌ ✅ ❌ ✅
SAM 3D Body ❌ ❌ ✅ ❌ ❌ ❌
EgoHumans ❌ ✅ ✅ ❌ ❌ ❌
EgoExo4D ✅ ❌ ❌ ✅ ❌ ❌

👥 Contributors

We welcome contributions! If you'd like to contribute, please submit a pull request or open an issue.

About

A collection and survey of 3d dataset

Resources

Readme
Activity

Stars

8 stars

Watchers

0 watching

Forks

1 fork
Report repository

Releases

No releases published

Packages

 
 
 

Contributors