Saved in:
Bibliographic Details
Main Authors: Tian, Qinyi, Cox, Spence, Dalton, Laura E.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.17708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914002758533120
author Tian, Qinyi
Cox, Spence
Dalton, Laura E.
author_facet Tian, Qinyi
Cox, Spence
Dalton, Laura E.
contents Super-resolution remains a promising technique to enhance the quality of low-resolution images. This study introduces CATformer (Contrastive Adversarial Transformer), a novel neural network integrating diffusion-inspired feature refinement with adversarial and contrastive learning. CATformer employs a dual-branch architecture combining a primary diffusion-inspired transformer, which progressively refines latent representations, with an auxiliary transformer branch designed to enhance robustness to noise through learned latent contrasts. These complementary representations are fused and decoded using deep Residual-in-Residual Dense Blocks for enhanced reconstruction quality. Extensive experiments on benchmark datasets demonstrate that CATformer outperforms recent transformer-based and diffusion-inspired methods both in efficiency and visual image quality. This work bridges the performance gap among transformer-, diffusion-, and GAN-based methods, laying a foundation for practical applications of diffusion-inspired transformers in super-resolution.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17708
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CATformer: Contrastive Adversarial Transformer for Image Super-Resolution
Tian, Qinyi
Cox, Spence
Dalton, Laura E.
Computer Vision and Pattern Recognition
Super-resolution remains a promising technique to enhance the quality of low-resolution images. This study introduces CATformer (Contrastive Adversarial Transformer), a novel neural network integrating diffusion-inspired feature refinement with adversarial and contrastive learning. CATformer employs a dual-branch architecture combining a primary diffusion-inspired transformer, which progressively refines latent representations, with an auxiliary transformer branch designed to enhance robustness to noise through learned latent contrasts. These complementary representations are fused and decoded using deep Residual-in-Residual Dense Blocks for enhanced reconstruction quality. Extensive experiments on benchmark datasets demonstrate that CATformer outperforms recent transformer-based and diffusion-inspired methods both in efficiency and visual image quality. This work bridges the performance gap among transformer-, diffusion-, and GAN-based methods, laying a foundation for practical applications of diffusion-inspired transformers in super-resolution.
title CATformer: Contrastive Adversarial Transformer for Image Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.17708