omnidirectional.md

Omnidirectional Depth Estimation

Estimate 360$^\circ$ depth maps from Fish-eye cameras

1. Sweepnet: Wide-baseline omnidirectional depth estimation. ICRA 2019. paper. code
2. Omnimvs: End-to-end learning for omnidirectional stereo matching. ICCV 2019. paper. code
3. End-to-end learning for omnidirectional stereo matching with uncertainty prior. IEEE TPAMI 2020. paper. code

Estimate 360$^\circ$ depth maps from Panoramas

Monocular

1. EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation. ICCV 2023. paper
2. PanoFormer: Panorama Transformer for Indoor 360° Depth Estimation. ECCV 2022. paper
3. OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion. CVPR 2022. paper. code.
4. 360MonoDepth: High-Resolution 360° Monocular Depth Estimation. CVPR 2022. paper. code
5. Unifuse: Unidirectional fusion for 360° panorama depth estimation. IEEE RAL 2021. paper. code
6. Spherical view synthesis for self-supervised 360° depth estimation. 3DV 2019. paper. code
7. Omnidepth: Dense depth estimation for indoors spherical panoramas. ECCV 2018. paper
8. Bifuse: Monocular 360 depth estimation via bi-projection fusion. CVPR 2020. paper, code

Binocular

1. 360sd-net: 360◦ stereo depth estimation with learnable cost volume. ICRA 2020. web. paper. code
2. Omnidirectional stereo depth estimation based on spherical deep network. IVC 2021. paper
3. Uniform Subdivision of Omnidirectional Camera Space for Efficient Spherical Stereo Matching. CVPR 2022. paper.

Multi-view

1. MODE: Multi-view Omnidirectional Depth Estimation with 360◦ Cameras. ECCV 2022. paper. code.