3D / Point Cloud
processed-3d-cache-indices
TrianguLang ScanNet++ Preprocessed Data Preprocessed depth maps, camera poses, pointmaps, and rasterized semantic masks for training and evaluating…
100K–1M·CC-BY-NC-SA
3D / Point Cloud
338 results
3D / Point CloudMultimodalText
StableText2Brick
Dataset Card for StableText2Brick This dataset contains over 47,000 toy brick structures of over 28,000 unique 3D objects…
10K–100K·MIT·Parquet
3D / Point CloudImageMultimodal
INR-benchmark
Signal Dataset Loader This repository provides a small collection of synthetic and real signals—both 2D and 3D—used for…
<1K·Other·Images (folder)
3D / Point Cloud
mixamo-characters
Mixamo Characters Dataset This dataset contains 3D character models from Mixamo in FBX format. Contents Format: FBX (Autodesk…
Custom / Research-only
3D / Point CloudImageMultimodal
3D CAD Models with Preview Images and Embeddings
3D CAD Models with Preview Images and Embeddings
100K–1M·Parquet
3D / Point CloudMultimodalText
Nano3D-Edit-100k
Nano3D-Edit-100k This dataset is the official data release for Nano3D, a training-free framework for precise and coherent 3D…
1M–10M·MIT·WebDataset
3D / Point CloudAudioImage
Edge Agent Reasoning WebSearch 260K
Edge Agent Reasoning WebSearch 260K
100K–1M·MIT·Parquet
3D / Point CloudMultimodalTabular
SHIFT-Crash-sample
SHIFT-Crash Sample: High-Fidelity Crash Simulation Dataset for Automotive Structural Mechanics We're excited to introduce the SHIFT-Crash Sample…
<1K·CC-BY-NC
3D / Point CloudImageMultimodal
reflect3r_synthetic_data
3DV 2026 Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflections Jing Wu, Zirui Wang, Iro Laina, Victor…
<1K·MIT·Images (folder)
3D / Point CloudImageMultimodal
PRISM
PRISM Paper arXiv Project Website Purpose-driven Robotic Interaction in Scene Manipulation (PRISM) is a large-scale synthetic dataset for…
100K–1M·MIT·CSV
3D / Point CloudMultimodalText
HouseLayout3D
HouseLayout3D: A Benchmark Dataset for 3D Layout Estimation in the Wild Paper Project Page Code HouseLayout3D is a…
10K–100K·MIT
3D / Point CloudMultimodalText
t2m4lvo-truebones-zoo
🐉 🐕🐊🦅🐀🦈 T2M4LVO: Text-to-Motion Synthesis for Large-Vocabulary Objects T2M4LVO is a high-quality, human-annotated dataset for text-to-motion…
1K–10K·CC-BY-NC·Parquet
3D / Point CloudImageMultimodal
ycb-fixed-meshes
This folder has updated versions of the YCB meshes. All updates are in google 16k folders for each…
<1K·CC-BY·Images (folder)