Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows

Seobin Park, Dong-Jin Kim, Sungyong Baik, Tae Hyun Kim
2/12/2026

No official code found. Best implementation: dongjinkim9/InterFlow (13 stars, MIT, last commit 2025-02-03).

Semantic Scholar

Code Implementations(1)

dongjinkim9/InterFlowCommunity59%
MIT

Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows, in ICML 2023

130C++, CudaMay 29, 20231 years agoMIT
real-image-super-resolutionsuper-resolution

Similar Papers

Discovering Clone Negatives via Adaptive Contrastive Learning for Image-Text Matching

99% match2026

Exact Fusion via Feature Distribution Matching for Few-Shot Image Generation

98% match2026

Robust Function-Calling for On-Device Language Model via Function Masking

98% match1 repo1152026

Learning Surrogates for Offline Black-Box Optimization via Gradient Matching

98% match1 repo72026

RetroInText: A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation Learning

98% match2026

In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment

98% match1 repo22026

Cite this paper

@article{park2026learning,
  title  = {Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows},
  author = {Seobin Park and Dong-Jin Kim and Sungyong Baik and Tae Hyun Kim},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:3e96f37f45fc147c83dd8f059e2b0abd57955cdb},
  journal = {ICML 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/3e96f37f45fc147c83dd8f059e2b0abd57955cdb.svg)](https://codeofpaper.com/paper/3e96f37f45fc147c83dd8f059e2b0abd57955cdb)

Discussion