crs4 / AtlantaNet
Pytorch implementation of the ECCV 2020 paper: AtlantaNet: Inferring the 3D Indoor Layout from a Single 360 Image beyond the Manhattan World Assumption
☆79Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for AtlantaNet
- "HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features" official pytorch implementation.☆108Updated last year
- PyTorch reimplementation of Omnidepth☆53Updated 4 years ago
- CVPR 2021 Oral paper "LED2-Net: Monocular 360˚ Layout Estimation via Differentiable Depth Rendering" official PyTorch implementation.☆109Updated 9 months ago
- Indoor Panorama Planar 3D Reconstruction via Divide and Conquer☆52Updated 3 years ago
- ☆80Updated 6 years ago
- Layout annotation on a subset of Matterport3D dataset☆63Updated 3 years ago
- [RA-L'22] 360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan Estimation☆53Updated 7 months ago
- Code and models for "Pano3D: A Holistic Benchmark and a Solid Baseline for 360 Depth Estimation", OmniCV Workshop @ CVPR21.☆82Updated 2 years ago
- BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation☆66Updated last year
- Learning to Reconstruct 3D Manhattan Wireframes from a Single Image☆69Updated 3 months ago
- ☆48Updated 4 years ago
- ☆14Updated 2 years ago
- ☆33Updated 2 years ago
- We introduce the ScanNet-Layout dataset for benchmarking general 3D room layout estimation from single view.☆33Updated 4 years ago
- ☆63Updated 3 years ago
- Tools accompanying the 3D60 spherical panoramas dataset☆104Updated 2 years ago
- Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image☆102Updated 2 years ago
- Official PyTorch code of DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimizat…☆89Updated 2 years ago
- [ECCV 2020] SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans☆76Updated 4 years ago
- [ECCV 2022] PlaneFormers: From Sparse View Planes to 3D Reconstruction☆83Updated 2 years ago
- (CVPR 2020) Neural Point Cloud Rendering via Multi-Plane Projection