AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Misalignment-Robust Joint Filter for Cross-Modal Image Pairs

Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

ICCV 2017 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 28 citations (OpenAlex)

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 changedWhereMeasuredEffect
apply the proposed weight-volume misalignment-robust filter on top of GFGF · NIR-guided denoising sigma=25PSNR: 27.33 -> 31.44Improved
apply the proposed method on top of GFGF · NIR-guided denoising sigma=50PSNR: 25.47 -> 28.00Improved
apply the proposed method on top of GFGF · NIR-guided denoising sigma=100PSNR: 21.41 -> 22.27Improved
apply the proposed method on top of JBFJBF · NIR-guided denoising sigma=25PSNR: 27.72 -> 31.40Improved
apply the proposed method on top of MSJFMSJF · NIR-guided denoising sigma=25PSNR: 25.84 -> 28.72Improved
add DASC registration before GF (aligned guidance) (ablation)GF · NIR-guided denoising sigma=25PSNR: 27.33 -> 29.56Improved
replace DASC-aligned guidance by the proposed weight volume (ablation)DASC+GF · NIR-guided denoising sigma=25PSNR: 29.56 -> 31.44Improved
use proposed JBF variant instead of BM3DBM3D · NIR-guided denoising sigma=25PSNR: 31.88 -> 31.40No clear effect
add DASC registration before GF (ablation)GF · FIR up-sampling x8RMSE: 6.644 -> 6.671Hurt
apply the proposed method on top of GFGF · FIR up-sampling x4RMSE: 3.964 -> 3.874Improved
apply the proposed method on top of GFGF · FIR up-sampling x8RMSE: 6.644 -> 6.252Improved
apply the proposed method on top of GFGF · FIR up-sampling x8SSIM: 0.8832 -> 0.8873Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy