Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A list of papers and resources (data,code,etc) for holistic 3D reconstruction in computer vision
| Date | Stars |
|---|---|
| 2026-07-24 | 646 |
| 2026-07-25 | 646 |
| 2026-07-28 | 646 |
| 2026-07-30 | 646 |
| 2026-07-31 | 646 |
| 2026-08-10 | 647 |
| 2026-08-18 | 647 |
| 2026-08-20 | 648 |
| 2026-08-27 | 649 |
| 2026-09-15 | 649 |
| 2026-09-20 | 649 |
Today
— stars today
This week
— stars this week
This month
+1 stars this month
Momentum
0.0
growth rate 0.00%/day
# Holistic 3D Reconstruction A list of papers and resources for holistic 3D reconstruction. ## Related Tutorials and Workshops - ECCV 2020 Workshop: [Holistic Scene Structures for 3D Vision](https://holistic-3d.github.io/eccv20/) - ICCV 2019 Tutorial: [Holistic 3D Reconstruction: Learning to Reconstruct Holistic 3D Structures from Sensorial Data](https://holistic-3d.github.io/iccv19/) ## Datasets ### Scene level | Datasets |#Scenes| #Rooms | #Frames | Annotated Structures | |------------|---------|---------|---------|---------| | [PlaneRCNN](https://github.com/NVlabs/planercnn) | ~1,500 | ~1,500 | 100,000 (randomly sampled from 1 million) | planes | | [Replica](https://github.com/facebookresearch/Replica-Dataset) | 18 | n/a | - | planes | | [Wireframe](https://github.com/huangkuns/wireframe) | - | - | 5,462 | wireframe (2D) | | [Wireframe Reconstruction](https://yichaozhou.com/publication/1811learning/) | synthetic and real images | - | - | wireframe (3D) | | [SUN Primitive](http://3dvision.princeton.edu/projects/2012/SUNprimitive/) | - | - | 785 | cuboid, pyramid, cylinder, sphere, etc. | | LSUN Room Layout | - | n/a | 5,394 | cuboid layout | | [PanoContext](http://panocontext.cs.princeton.edu/) | - | n/a | 500 (pano) | cuboid layout | | [LayoutNet](https://github.com/zouchuhang/LayoutNet) | - | n/a | 1,071 (pano) | cuboid layout | | [MatterportLayout](https://github.com/ericsujw/Matterport3DLayoutAnnotation) | - | n/a | 2,295 (RGB-D pano) | Manhattan layout | | [Floor-SP](https://github.com/woodfrog/floor-sp) | 100 | 707 | ~1500 (every scene has a set of RGB-D pano) | floorplan (with non-Manhattan structures) | | [FloorNet](https://github.com/art-programmer/FloorNet) | ~150 | ~1000 | - | floorplan | | [Raster-to-Vector](https://github.com/art-programmer/FloorplanTransformation) | 870 | - | - | floorplan | | [3RScan](https://waldjohannau.github.io/RIO/) | 478 | - | - | objects | | [Structured3D](https://structured3d-dataset.org/) | 3,500 | 21,835 | 196,515 | pritimitves (points/lines/planes) and relationships, 3D object instance bounding boxes| ### Object level | Datasets |#Images | #Categories | #3D models | Annotated Structures | Notes | |------------|---------|---------|---------|---------|---------| | [Keypoint-5](http://3dinterpreter.csail.mit.edu/) | 8,649 | 5 | - | keypoints | | | [IKEA Keypoints](http://3dinterpreter.csail.mit.edu/) | 759 | | 219 | keypoints | derived from [IKEA 3D](http://ikea.csail.mit.edu/) | | [ANSI Mechanical Component](https://github.com/lingxiaoli94/SPFN) | - | 504 | 17,197 | plane, sphere, cylinder, cone, etc.| | | [PartNet](https://cs.stanford.edu/%7Ekaichun/partnet/) | - | 24 | 26,671 | fine-grained, instance-level, and hierarchical 3D parts | derived from ShapeNet | | [PartNet-Symh](https://github.com/FoggYu/PartNet_symh/) | - | 24 | 22,369 | Symmetry hierarchical 3D parts | derived from PartNet | | [StructureNet](https://cs.stanford.edu/~kaichun/structurenet/) | - | 6 | - | Symmetry hierarchical 3D parts | derived from PartNet | ### Datasets examples [PlaneRCNN](https://github.com/NVlabs/planercnn) <div align="center"> <img src=figures/PlaneRCNN.jpg> </div> <div align="center">From left to right: input RGB image, planar segmentation, depthmap</div> [Wireframe](https://github.com/huangkuns/wireframe) <div align="center"> <img src=figures/Wireframe.jpg> </div> <div align="center">First row: manually labelled line segments. Second row: groundtruth junctions</div> [Wireframe Reconstruction](https://yichaozhou.com/publication/1811learning/) <div align="center"> <img src=figures/Wireframe_reconstruction.jpg> </div> <div align="center">From left column to right column: input image with groundtruth wireframes, predicted 3D wireframe and alternative view of the same image</div> [SUN Primitive](http://3dvision.princeton.edu/projects/2012/SUNprimitive/) <div align="center"> <img src=figures/SUN_Primitive.jpg> </div> <div align="center">Yellow: groundtruth, green
Excerpt of 25,981 characters
Read on GitHub
30
Jia Zheng · @manycore-research
5
2
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:e7626373ce243182, topic:computer-vision, topic:3d-reconstruction, desc:computer vision
matched fp:e7626373ce243182, topic:awesome, desc:a list of, readme:a list of