 |
|
3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics (2020)
A large-scale repository specific to interior layouts. It contains 6,813 houses (or apartments) and ~44,443 rooms with layout information. Furthermore, it provides verified exquisite interior designs for ~18,797 rooms.
Link
|
|
 |
|
3D-FUTURE: 3D FUrniture shape with TextURE (2020)
A dataset provides 9,992 unique high quality 3D instances of furniture with high resolution informative textures developed by professional designers.
Link
|
|
 |
|
Segmented meshes in ShapeNet (2019)
A dataset provides segmentation information for models in ShapeNet.
Link
|
|
 |
|
ABC: A Big CAD Model Dataset For Geometric Deep Learning (2019)
One million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications.
Link
|
|
 |
|
Thingi10K: A Dataset of 10,000 3D-Printing Models (2016)
A large scale 3D dataset created to study the variety, complexity and quality of real-world 3D printing models.
Link
|
|
 |
|
A Large Dataset of Object Scans (2016)
10K scans in RGBD + reconstructed 3D models in .PLY format.
The RGB-D sequences were acquired with PrimeSense Carmine cameras. The resolution is 640x480, the frame rate is 30Hz.
Link
|
|
 |
|
SUNRGB-D 3D Object Detection Challenge (2015)
19 object categories for predicting a 3D bounding box in real world dimension.
Training set: 10,355 RGB-D scene images, Testing set: 2860 RGB-D images.
Link
|
|
 |
|
ShapeNet (2015)
3Million+ models and 4K+ categories. A dataset that is large in scale, well organized and richly annotated.
ShapeNetCore: 51300 models for 55 categories.
ShapeNetSem: 12,000 models for 270 categories.
Link
|
|
 |
|
ModelNet (2015)
127915 3D CAD models from 662 categories.
ModelNet10: 4899 models from 10 categories.
ModelNet40: 12311 models from 40 categories, all are uniformly orientated.
Link
|
|
 |
|
Labeled PSB Dataset (2010)
Contain the indices of faces belonging to each label per mesh.
The meshes and segmentations come from the Princeton Segmentation Benchmark.
Link
|
|
 |
|
Princeton Shape Benchmark (2003)
1,814 models collected from the web in .OFF format. Used to evaluating shape-based retrieval and analysis algorithms.
Link
|
|