AI Paper Atlas

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

CVPR 2026 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 18 citations (OpenAlex)

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 changedWhereMeasuredEffect
add distortion map to SILog-only baseline (ablation)DAP · Deep360AbsRel: 0.0942 -> 0.0926Improved
add geometry losses (normal, point cloud) (ablation)DAP · Stanford2D3DAbsRel: 0.1149 -> 0.1112Improved
add sharpness losses (DF, gradient) (ablation)DAP · Deep360AbsRel: 0.0880 -> 0.0862Improved
add sharpness losses (DF, gradient) (ablation)DAP · Stanford2D3DRMSE: 0.448 -> 0.442Improved
add distortion map (ablation)DAP · Stanford2D3DRMSE: 0.449 -> 0.449No clear effect
add range mask head (100 m) (ablation)DAP · Deep360AbsRel: 0.0938 -> 0.0862Improved
add range mask head (100 m) (ablation)DAP · DAP-2M-Labeleddelta1: 0.9042 -> 0.9353Improved
use 10 m mask instead of 100 m (ablation)DAP · Deep360AbsRel: 0.0862 -> 0.0934Hurt
three-stage pseudo-label training on 2M panoramas vs prior metric methodsDAP vs Unik3D · Deep360AbsRel: 0.0885 -> 0.0659 (vs Unik3D)Improved
DAP vs Unik3D on Matterport3DDAP vs Unik3D · Matterport3DAbsRel: 0.2224 -> 0.1186Improved
DAP vs scale-invariant DA2 (reference only)DAP vs DA2 · Stanford2D3DAbsRel: 0.0723 vs 0.0921Hurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy