AI Paper Atlas

Research map / 3D vision / Depth and stereo

Deep Surface Normal Estimation on the 2-Sphere with Confidence Guided Semantic Attention

Quewei Li, Jie Guo, Yang Fei, Qinyu Tang, Wenxiu Sun, Jin Zeng, Yanwen Guo

ECCV 2020 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 2 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
estimate normals on the 2-sphere (polar coordinates) instead of R3 (ablation)surface normal network with MFF and CGSA · NYUD-v2mean angle error (deg): 12.850 -> 12.172Improved
estimate normals on the 2-sphere instead of R3 (ablation)surface normal network with MFF and CGSA · Matterport3Dmean angle error (deg): 15.903 -> 14.687Improved
estimate normals on the 2-sphere instead of R3 (ablation)surface normal network with MFF and CGSA · ScanNetmean angle error (deg): 14.205 -> 13.508Improved
estimate normals on the 2-sphere instead of R3 (ablation)surface normal network with MFF and CGSA · NYUD-v2accuracy within 11.25 deg (%): 66.39 -> 69.41Improved
add the CGSA module (ablation)surface normal network with MFF and CGSA · NYUD-v2mean angle error (deg): 12.790 -> 12.172Improved
add the CGSA module (ablation)surface normal network with MFF and CGSA · Matterport3Dmean angle error (deg): 16.147 -> 14.687Improved
add the CGSA module (ablation)surface normal network with MFF and CGSA · ScanNetmean angle error (deg): 14.390 -> 13.508Improved
add the MFF module (ablation)surface normal network with MFF and CGSA · NYUD-v2mean angle error (deg): 13.001 -> 12.172Improved
add the MFF module (ablation)surface normal network with MFF and CGSA · Matterport3Dmean angle error (deg): 15.768 -> 14.687Improved
add the MFF module (ablation)surface normal network with MFF and CGSA · ScanNetmean angle error (deg): 14.425 -> 13.508Improved
add the CGSA module (ablation)surface normal network with MFF and CGSA · NYUD-v2accuracy within 11.25 deg (%): 65.66 -> 69.41Improved
add the MFF module (ablation)surface normal network with MFF and CGSA · NYUD-v2accuracy within 11.25 deg (%): 65.31 -> 69.41Improved

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