{"ID":6620672,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.12753","arxiv_id":"2607.12753","title":"RFMSR: Residual Flow Matching for Image Super-Resolution","abstract":"Image super-resolution (ISR) has witnessed remarkable progress with diffusion models and flow matching. The dominant text-to-image (T2I) based approaches leverage large-scale foundation models as generative priors, achieving impressive perceptual quality but at the cost of massive model sizes and prohibitive training expenses. Recent flow-matching-based vision-only approaches have made significant strides; however, they adopt standard flow formulations that transport from a pure Gaussian prior to the data distribution, discarding the rich structural information already present in the low-quality (LQ) input. Furthermore, existing single-step acceleration techniques often forfeit the model's multi-step inference capability. In this paper, we propose Residual Flow Matching for Image Super-Resolution (RFMSR), a vision-only framework that centers the source distribution at the LQ latent, reducing transport distance and preserving structural priors throughout the flow trajectory. We further introduce a two-phase training strategy: Phase I pretrains the velocity field via conditional flow matching, while Phase II applies end-to-end supervision to the single-step prediction while retaining the velocity loss across all timesteps, achieving high-quality single-step generation without sacrificing multi-step refinement. Extensive experiments demonstrate that RFMSR achieves comparable or even superior perceptual quality compared to state-of-the-art (SOTA) methods. The source code is available at https://github.com/Faze-Hsw/RFMSR.","short_abstract":"Image super-resolution (ISR) has witnessed remarkable progress with diffusion models and flow matching. The dominant text-to-image (T2I) based approaches leverage large-scale foundation models as generative priors, achieving impressive perceptual quality but at the cost of massive model sizes and prohibitive training e...","url_abs":"https://arxiv.org/abs/2607.12753","url_pdf":"https://arxiv.org/pdf/2607.12753v1","authors":"[\"Shuwei Huang\",\"Tianyao Luo\",\"Jicheng Liu\",\"Daizong Liu\",\"Pan Zhou\"]","published":"2026-07-14T13:19:36Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":614253,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T01:01:48.440468303Z","DeletedAt":null,"paper_id":6620672,"paper_url":"https://arxiv.org/abs/2607.12753","paper_title":"RFMSR: Residual Flow Matching for Image Super-Resolution","repo_url":"https://github.com/Faze-Hsw/RFMSR","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}