Research map / Image generation / Image restoration
Spatially Variant Linear Representation Models for Joint Filtering
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SVLRM with CNN-estimated spatially variant coefficients instead of DJF | Depth image upsampling · NYU depth upsampling ×4 | RMSE: 3.54 -> 1.74 | Helped |
| use SVLRM with CNN-estimated spatially variant coefficients instead of DJF | Depth image upsampling · NYU depth upsampling ×8 | RMSE: 6.20 -> 5.59 | Helped |
| use SVLRM with CNN-estimated spatially variant coefficients instead of DJF | Depth image upsampling · NYU depth upsampling ×16 | RMSE: 10.21 -> 7.23 | Helped |
| use SVLRM joint restoration instead of MUGIF | Depth image restoration · Depth image restoration | Avg. PSNRs: 34.07 -> 36.44 | Helped |
| use SVLRM joint restoration instead of MUGIF | Depth image restoration · Depth image restoration | Avg. SSIMs: 0.9657 -> 0.9762 | Helped |
| use SVLRM joint restoration instead of MUGIF | Depth image restoration · Depth image restoration | Avg. RMSEs: 5.26 -> 4.02 | Helped |
| use SVLRM denoising instead of IRCNN | Natural image denoising · BSDS image denoising | Avg. PSNRs: 31.86 -> 33.04 | Helped |
| use SVLRM denoising instead of IRCNN | Natural image denoising · BSDS image denoising | Avg. SSIMs: 0.8811 -> 0.8957 | Helped |
| use SVLRM denoising instead of IRCNN | Natural image denoising · BSDS image denoising | Avg. RMSEs: 6.64 -> 6.32 | Helped |
| add SVLRM coefficient learning rather than directly predicting the target image (ablation) | Depth image denoising · Depth image denoising | Avg. PSNRs: 35.31 -> 35.98 | Helped |
| add SVLRM coefficient learning rather than directly predicting the target image (ablation) | Natural image denoising · Natural image denoising | Avg. PSNRs: 32.44 -> 33.04 | Helped |
| add CNN-estimated SVLRM coefficients instead of hand-crafted coefficient priors (ablation) | Depth image denoising · Depth image denoising | Avg. PSNRs: 21.84 -> 35.98 | Helped |
Closest papers by meaning
- Fast End-to-End Trainable Guided Filter (CVPR 2018 · similarity 0.87)
- Learning Factorized Weight Matrix for Joint Filtering (ICML 2020 · similarity 0.85)
- CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters (CVPR 2022 · similarity 0.84)
- Joint Demosaicing and Denoising With Self Guidance (CVPR 2020 · similarity 0.83)
- Improving Robustness for Joint Optimization of Camera Pose and Decomposed Low-Rank Tensorial Radiance Fields (AAAI 2024 · similarity 0.83)
- Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning (NeurIPS 2025 · similarity 0.82)
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.