Research map / Vision-language and multimodal / Cross-modal learning
Misalignment-Robust Joint Filter for Cross-Modal Image Pairs
Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi
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 |
|---|---|---|---|
| apply the proposed weight-volume misalignment-robust filter on top of GF | GF · NIR-guided denoising sigma=25 | PSNR: 27.33 -> 31.44 | Improved |
| apply the proposed method on top of GF | GF · NIR-guided denoising sigma=50 | PSNR: 25.47 -> 28.00 | Improved |
| apply the proposed method on top of GF | GF · NIR-guided denoising sigma=100 | PSNR: 21.41 -> 22.27 | Improved |
| apply the proposed method on top of JBF | JBF · NIR-guided denoising sigma=25 | PSNR: 27.72 -> 31.40 | Improved |
| apply the proposed method on top of MSJF | MSJF · NIR-guided denoising sigma=25 | PSNR: 25.84 -> 28.72 | Improved |
| add DASC registration before GF (aligned guidance) (ablation) | GF · NIR-guided denoising sigma=25 | PSNR: 27.33 -> 29.56 | Improved |
| replace DASC-aligned guidance by the proposed weight volume (ablation) | DASC+GF · NIR-guided denoising sigma=25 | PSNR: 29.56 -> 31.44 | Improved |
| use proposed JBF variant instead of BM3D | BM3D · NIR-guided denoising sigma=25 | PSNR: 31.88 -> 31.40 | No clear effect |
| add DASC registration before GF (ablation) | GF · FIR up-sampling x8 | RMSE: 6.644 -> 6.671 | Hurt |
| apply the proposed method on top of GF | GF · FIR up-sampling x4 | RMSE: 3.964 -> 3.874 | Improved |
| apply the proposed method on top of GF | GF · FIR up-sampling x8 | RMSE: 6.644 -> 6.252 | Improved |
| apply the proposed method on top of GF | GF · FIR up-sampling x8 | SSIM: 0.8832 -> 0.8873 | Improved |
Closest papers by meaning
- Robust Guided Image Filtering Using Nonconvex Potentials (TPAMI 2017 · similarity 0.84)
- Jointly Aligning Millions of Images With Deep Penalised Reconstruction Congealing (ICCV 2019 · similarity 0.83)
- Mutually Guided Image Filtering (TPAMI 2018 · similarity 0.83)
- Spatially Variant Linear Representation Models for Joint Filtering (CVPR 2019 · similarity 0.83)
- Misalignment-Robust Frequency Distribution Loss for Image Transformation (CVPR 2024 · similarity 0.83)
- FastJAM: a Fast Joint Alignment Model for Images (NeurIPS 2025 · similarity 0.80)
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.
