RFMSR: Residual Flow Matching for Image Super-Resolution
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-quali
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 58%[Paper] Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling →
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “RFMSR: Residual Flow Matching for Image Super-Resolution” ≈ “Tongyi-MAI/Z-Image-Turbo””
- LinkedLinked via arxiv author · 85%Shuwei Huang →
“RFMSR: Residual Flow Matching for Image Super-Resolution”
- LinkedLinked via arxiv author · 85%Tianyao Luo →
“RFMSR: Residual Flow Matching for Image Super-Resolution”
- LinkedLinked via arxiv author · 85%Jicheng Liu →
“RFMSR: Residual Flow Matching for Image Super-Resolution”
- LinkedLinked via arxiv author · 85%Daizong Liu →
“RFMSR: Residual Flow Matching for Image Super-Resolution”
- LinkedLinked via arxiv author · 85%Pan Zhou →
“RFMSR: Residual Flow Matching for Image Super-Resolution”
- FuzzyOverlapping authors or contributors · 78%sgl-project/sglang →
“Shared author/contributor keys: luo, zhou”