Research map / 3D vision / Depth and stereo
Monocular Normal Estimation via Shading Sequence Estimation
Zongrui Li, Xinhua Ma, Minghui Hu, Yunqing Zhao, Yingchen Yu, Qian Zheng, Chang Liu, Xudong Jiang, Song Bai
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 negative-clamping of the shading sequence (ablation) | RoSE · LUCES | MAE (degrees): 15.88 -> 14.48 | Improved |
| add material augmentation to training data (ablation) | RoSE · LUCES | MAE (degrees): 16.19 -> 14.48 | Improved |
| train Lotus-G on MultiShade (ablation) | Lotus-G · LUCES | MAE (degrees): 17.44 -> 17.36 | Improved |
| train Lotus-G on MultiShade (ablation) | Lotus-G · LUCES (House) | MAE (degrees): 35.32 -> 38.90 | Hurt |
| train RoSE on MultiShade instead of LightProp (ablation) | RoSE · LUCES | MAE (degrees): 15.21 -> 14.48 | Improved |
| use grayscale input instead of RGB (ablation) | RoSE · LUCES | MAE (degrees): 15.27 -> 14.48 | Improved |
| use ring-light path instead of spiral light path (ablation) | RoSE · LUCES | MAE (degrees): 17.60 -> 14.48 | Improved |
| swap SV3D backbone for SVD XL (ablation) | RoSE · LUCES | MAE (degrees): 14.48 -> 14.58 | No clear effect |
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.
- GeoWizard — GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image (ECCV 2024) · 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
- DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images (ECCV 2022 · similarity 0.87)
- Intrinsic Scene Properties from a Single RGB-D Image (TPAMI 2016 · similarity 0.86)
- Poppy: Polarization-Based Plug-and-Play Guidance for Enhancing Surface Normal Estimation (ECCV 2026 · similarity 0.86)
- Hierarchical Normalization for Robust Monocular Depth Estimation (NeurIPS 2022 · similarity 0.85)
- DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generation (AAAI 2025 · similarity 0.85)
- Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion (CVPR 2025 · similarity 0.85)
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.
