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
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 |
|---|---|---|---|
| estimate normals on the 2-sphere (polar coordinates) instead of R3 (ablation) | surface normal network with MFF and CGSA · NYUD-v2 | mean angle error (deg): 12.850 -> 12.172 | Improved |
| estimate normals on the 2-sphere instead of R3 (ablation) | surface normal network with MFF and CGSA · Matterport3D | mean angle error (deg): 15.903 -> 14.687 | Improved |
| estimate normals on the 2-sphere instead of R3 (ablation) | surface normal network with MFF and CGSA · ScanNet | mean angle error (deg): 14.205 -> 13.508 | Improved |
| estimate normals on the 2-sphere instead of R3 (ablation) | surface normal network with MFF and CGSA · NYUD-v2 | accuracy within 11.25 deg (%): 66.39 -> 69.41 | Improved |
| add the CGSA module (ablation) | surface normal network with MFF and CGSA · NYUD-v2 | mean angle error (deg): 12.790 -> 12.172 | Improved |
| add the CGSA module (ablation) | surface normal network with MFF and CGSA · Matterport3D | mean angle error (deg): 16.147 -> 14.687 | Improved |
| add the CGSA module (ablation) | surface normal network with MFF and CGSA · ScanNet | mean angle error (deg): 14.390 -> 13.508 | Improved |
| add the MFF module (ablation) | surface normal network with MFF and CGSA · NYUD-v2 | mean angle error (deg): 13.001 -> 12.172 | Improved |
| add the MFF module (ablation) | surface normal network with MFF and CGSA · Matterport3D | mean angle error (deg): 15.768 -> 14.687 | Improved |
| add the MFF module (ablation) | surface normal network with MFF and CGSA · ScanNet | mean angle error (deg): 14.425 -> 13.508 | Improved |
| add the CGSA module (ablation) | surface normal network with MFF and CGSA · NYUD-v2 | accuracy within 11.25 deg (%): 65.66 -> 69.41 | Improved |
| add the MFF module (ablation) | surface normal network with MFF and CGSA · NYUD-v2 | accuracy within 11.25 deg (%): 65.31 -> 69.41 | Improved |
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.
- GeoNet — GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation (CVPR 2018) · better on 3 of 3 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
- Just Look at the Image: Viewpoint-Specific Surface Normal Prediction for Improved Multi-View Reconstruction (CVPR 2016 · similarity 0.88)
- GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation (CVPR 2018 · similarity 0.88)
- Deep Surface Normal Estimation With Hierarchical RGB-D Fusion (CVPR 2019 · similarity 0.88)
- Surface Normals in the Wild (ICCV 2017 · similarity 0.87)
- VPLNet: Deep Single View Normal Estimation With Vanishing Points and Lines (CVPR 2020 · similarity 0.87)
- GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation (TPAMI 2020 · similarity 0.87)
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.
