Research map / Image generation / Super-resolution
Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution
Zixiang Zhao, Jiangshe Zhang, Xiang Gu, Chengli Tan, Shuang Xu, Yulun Zhang, Radu Timofte, Luc Van Gool
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 |
|---|---|---|---|
| use private (separate) encoders and decoders for RGB and depth instead of shared (ablation) | SSDNet · RGBDD x8 | RMSE: 2.10 -> 1.72 | Improved |
| use private (separate) encoders and decoders for RGB and depth instead of shared (ablation) | SSDNet · RGBDD x16 | RMSE: 3.49 -> 2.92 | Improved |
| add spherical feature decomposition loss (ablation) | SSDNet · RGBDD x8 | RMSE: 1.94 -> 1.72 | Improved |
| add spherical feature decomposition loss (ablation) | SSDNet · RGBDD x16 | RMSE: 3.27 -> 2.92 | Improved |
| use spherical distance instead of l2 distance in decomposition loss (ablation) | SSDNet · RGBDD x8 | RMSE: 1.83 -> 1.72 | Improved |
| use spherical distance instead of l2 distance in decomposition loss (ablation) | SSDNet · RGBDD x16 | RMSE: 3.06 -> 2.92 | Improved |
| add RGB reconstruction loss (ablation) | SSDNet · RGBDD x8 | RMSE: 1.89 -> 1.72 | Improved |
| add RGB reconstruction loss (ablation) | SSDNet · RGBDD x16 | RMSE: 3.29 -> 2.92 | Improved |
| add spherical contrast refinement module (ablation) | SSDNet · RGBDD x8 | RMSE: 1.87 -> 1.72 | Improved |
| add spherical contrast refinement module (ablation) | SSDNet · RGBDD x16 | RMSE: 3.36 -> 2.92 | Improved |
| add spherical feature decomposition loss (ablation) | SSDNet · RGBDD x4 | RMSE: 1.17 -> 1.04 | Improved |
| add spherical contrast refinement module (ablation) | SSDNet · RGBDD x4 | RMSE: 1.18 -> 1.04 | Improved |
Closest papers by meaning
- Discrete Cosine Transform Network for Guided Depth Map Super-Resolution (CVPR 2022 · similarity 0.88)
- Decoupling Fine Detail and Global Geometry for Compressed Depth Map Super-Resolution (CVPR 2025 · similarity 0.86)
- SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-resolution (AAAI 2024 · similarity 0.86)
- DegBins: Degradation-Driven Binning for Depth Super-Resolution (NeurIPS 2026 · similarity 0.86)
- DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution (CVPR 2025 · similarity 0.84)
- Intrinsic Phase-Preserving Networks for Depth Super Resolution (AAAI 2024 · similarity 0.84)
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.
