Research map / Learning theory and algorithms / Matrix and tensor methods
Nonlocal Patch Based t-SVD for Image Inpainting: Algorithm and Error Analysis
Liangchen Song, Bo Du, Lefei Zhang, Liangpei Zhang, Jia Wu, Xuelong Li
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 |
|---|---|---|---|
| nonlocal patch grouping + interpolation + t-SVD instead of plain global t-SVD | t-SVD · Lena, 80% missing | PSNR (dB): 20.84 -> 27.28 | Improved |
| nonlocal patch grouping + interpolation + t-SVD instead of plain global t-SVD | t-SVD · Facade, 50% missing | PSNR (dB): 30.83 -> 28.69 | Hurt |
| replace t-SVD completion step with FBCP in the patch framework (ablation) | Ours · Lena, 80% missing | PSNR (dB): 27.28 -> 21.65 | Hurt |
| replace t-SVD completion step with HaLRTC in the patch framework (ablation) | Ours · Lena, 80% missing | PSNR (dB): 27.28 -> 8.64 | Hurt |
| replace t-SVD completion step with HaLRTC in the patch framework (ablation) | Ours · Lena, 20% missing | PSNR (dB): 37.39 -> 35.77 | Hurt |
| patch-based version of FBCP instead of global FBCP | FBCP · Lena, 80% missing | PSNR (dB): 23.51 -> 21.65 | Hurt |
| patch-based version of FBCP instead of global FBCP | FBCP · Lena, 60% missing | PSNR (dB): 27.84 -> 30.05 | Improved |
| warm start of dual variable and adaptive rho update instead of vanilla warm start (Q0=0) (ablation) | ADMM in Ours · Facade grayscale, 70% missing | PSNR (dB) | Improved |
Closest papers by meaning
- Low-Rank Tensor Completion with Total Variation for Visual Data Inpainting (AAAI 2017 · similarity 0.86)
- Handling The Non-Smooth Challenge in Tensor SVD: A Multi-Objective Tensor Recovery Framework (ECCV 2024 · similarity 0.85)
- Contextual-based Image Inpainting: Infer, Match, and Translate (ECCV 2018 · similarity 0.84)
- High-Resolution Image Inpainting Using Multi-Scale Neural Patch Synthesis (CVPR 2017 · similarity 0.84)
- InpDiffusion: Image Inpainting Localization via Conditional Diffusion Models (AAAI 2025 · similarity 0.82)
- Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model (NeurIPS 2024 · 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.
