cs.CVNov 2, 2026

Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement

Authors: Chun-An Lin, Yu-Chia Chang, Chi-Mao Fan, Yen-Chieh Ouyang, Tsung-Jung Liu

Organizations: Department of Electrical Engineering, National Chung Hsing University, Taichung 402202, Taiwan · College of Computing and Informatics, Providence University, Taichung 433303, Taiwan · ASUSTeK Computer Inc., Taipei 112019, Taiwan

Abstract

Super-resolution networks are trained for one magnification factor, so several output resolutions require several models. We propose PMS-SR, a progressive single-input multiple-output network that produces x2, x4, and x8 results in one forward pass, with a Transformer backbone on the low-resolution grid. In Stage 1, each scale is predicted as a residual over the detached bicubic upsampling of the previous scale's prediction. With Dirac and zero initialization, training starts exactly from the bicubic cascade, and each head adds only the band the previous scale lacks. In Stage 2, inter-scale mutual refinement couples the scales in both directions through space-to-depth feedback, deformable alignment, and per-pixel fusion, so x8 features refine the x2 output. Trained on DF2K, the 7.95M-parameter model achieves a higher PSNR than every compared multi-scale method at x4 and x8 on all five standard benchmarks. At x8, it outperforms the x8-specific DRN-L on all of them, leads all compared methods on Urban100, and is within 0.13 dB of the best result elsewhere. Against three single-scale SwinIR-M models, PMS-SR uses 22% of the parameters, runs 2.9x faster on BSD100 inputs, and its outputs agree 6.7-12.4 dB more closely. Code and pretrained models will be released at https://github.com/julian135707/PMS-SR upon acceptance.

Figures & tables

Explore similar work

CardsList
  1. FreeTransformSR: Efficient Lightweight Image Super-Resolution via Free Low-Rank Learnable Transform

    Sep 5, 2026Hongji Li, Yunhui Li, Jianing Wang +1Hybrid CNN-Transformer ArchitecturesImage Super-Resolution