cs.CVNov 17, 2026

Unified Residual Translation for Paired Image Restoration

Authors: Joyanta Jyoti Mondal, Mridul Banik, Ibne Farabi Shihab, Md. Shifatul Ahsan Apurba

Organizations: University of Delaware · BRAC University · Indiana University Indianapolis · University of Alabama at Birmingham

Abstract

Paired image restoration spans changes in imaging contrast, sensor modality, and spatial resolution. These settings differ in their input channels and target grids, raising the question of how much of the prediction pipeline must be specialized to each task. We present the Unified Residual Translator (URT), which separates fixed channel and scale mapping from learned residual prediction. A deterministic reference uses channel averaging, replication, or bicubic interpolation to match the target dimensions, while a NAFNet encoder-decoder predicts an additive correction from the complete input. Separately trained instances share the prediction rule, ℓ1\ell_1 objective, and optimizer across MRI contrast synthesis, visible-to-infrared translation, SAR-to-optical translation, and real-camera super-resolution. Across six task and scale settings, URT achieves the highest PSNR and SSIM among the evaluated baselines on IXI, SEN1-2, and RealSR ×3\times3 and ×4\times4. It reaches 30.774dB on IXI and 13.478dB on SEN1-2, with luminance PSNR of 33.596, 28.742, and 27.342dB at the three RealSR scales. On LLVIP, it ranks second in PSNR and SSIM. A study of four spectral alternatives identifies complementary benefits of fitted references and bandwise residual gains. Together, these results support explicit dimensional alignment and learned residual correction as a common formulation for heterogeneous paired imaging tasks.

Figures & tables

Explore similar work

CardsList
  1. Ultra-High-Definition Restoration Transformers with Correlation Matching Transformation

    Aug 18, 2026Cong Wang, Liyan Wang, Jinshan Pan +4Image RestorationAll-in-One Image Restoration

  2. Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation

    May 31, 2026Ziyue Lin, Jiahe Hou, Hongyu Xia +6Diffusion Model AlignmentImage-to-Image Translation

  3. Language-Assisted Super-Resolution from Real-World Low-Resolution Patches

    Jun 30, 2026Joonkyu Park, Kyoung Mu LeeImage Super-Resolution