Research map / 3D vision / Depth and stereo
Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation
Xin Lin, Meixi Song, Dizhe Zhang, Wenxuan Lu, Haodong Li, Bo Du, Ming-Hsuan Yang, Truong Nguyen, Lu Qi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add distortion map to SILog-only baseline (ablation) | DAP · Deep360 | AbsRel: 0.0942 -> 0.0926 | Improved |
| add geometry losses (normal, point cloud) (ablation) | DAP · Stanford2D3D | AbsRel: 0.1149 -> 0.1112 | Improved |
| add sharpness losses (DF, gradient) (ablation) | DAP · Deep360 | AbsRel: 0.0880 -> 0.0862 | Improved |
| add sharpness losses (DF, gradient) (ablation) | DAP · Stanford2D3D | RMSE: 0.448 -> 0.442 | Improved |
| add distortion map (ablation) | DAP · Stanford2D3D | RMSE: 0.449 -> 0.449 | No clear effect |
| add range mask head (100 m) (ablation) | DAP · Deep360 | AbsRel: 0.0938 -> 0.0862 | Improved |
| add range mask head (100 m) (ablation) | DAP · DAP-2M-Labeled | delta1: 0.9042 -> 0.9353 | Improved |
| use 10 m mask instead of 100 m (ablation) | DAP · Deep360 | AbsRel: 0.0862 -> 0.0934 | Hurt |
| three-stage pseudo-label training on 2M panoramas vs prior metric methods | DAP vs Unik3D · Deep360 | AbsRel: 0.0885 -> 0.0659 (vs Unik3D) | Improved |
| DAP vs Unik3D on Matterport3D | DAP vs Unik3D · Matterport3D | AbsRel: 0.2224 -> 0.1186 | Improved |
| DAP vs scale-invariant DA2 (reference only) | DAP vs DA2 · Stanford2D3D | AbsRel: 0.0723 vs 0.0921 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Unik3D — UniK3D: Universal Camera Monocular 3D Estimation (CVPR 2025) · better on 11 of 12 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images (NeurIPS 2026 · similarity 0.92)
- Unified Panoramic Geometry Estimation via Multi-View Foundation Models (NeurIPS 2026 · similarity 0.91)
- PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation (CVPR 2025 · similarity 0.90)
- Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images (CVPR 2025 · similarity 0.89)
- Depth Anything V2 (NeurIPS 2024 · similarity 0.88)
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data (CVPR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
