neosr is an open-source framework for training super-resolution models.

[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

[ICLR 2024] Controlling Vision-Language Models for Universal Image Restoration. 5th place in the NTIRE 2024 Restore Any Image Model in the Wild Challenge.

Arxiv - Partial Large Kernel CNNs for Efficient Super-Resolution

The official repository of BFSR: "Boosting Flow-based Generative Super-Resolution Models via Learned Prior" [CVPR 2024]

[CVPR 2024] Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024)

Official implementation of the paper "DeblurDiNAT: A Generalizable Transformer for Perceptual Image Deblurring".

Accelerating Image Super-Resolution Networks with Pixel-Level Classification (ECCV 2024)

A sketch extractor for anime/illustration.

[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

(ECCV 2020) RANSAC-Flow: generic two-stage image alignment

[TMLR 2025] Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields