Wavelet Convolutions for Large Receptive Fields. ECCV 2024.

Dataset and Code for ICCV 2021 paper "Real-world Video Super-resolution: A Benchmark Dataset and A Decomposition based Learning Scheme"

Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices, ACM Multimedia 2021

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention (CVPR 2022)

[CVPR 2023] Effcient Frequence Domain-based Transformer for High-Quality Image Deblurring

edge-SR: Super-Resolution For The Masses

AAAI-2024 KeDuSR: Real-World Dual-Lens Super-Resolution via Kernel-Free Matching

[ICCV 2021 (Oral Presentation)] Dual-Camera Super-Resolution with Aligned Attention Modules (RefSR)

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

Video datasets

📚 A collection of sketch based application papers.

ECCV24-PoseSOR: Human Pose Can Guide Our Attention

Repository of the paper "Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules"

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

[CVPR 2024 Oral] Official repository of FMA-Net

A PyTorch implementation of widely-used bicubic interpolation, which is fully compatible with MATLAB.

Official dataset and codes of Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World[CVPR2024].

Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey [Miyai+, arXiv2024]

This is the PyTorch implementation of paper: FSR (AAAI 2023 Oral).

[CVPR 2020] The first large-scale public benchmark dataset for image harmonization. The code used in our paper "DoveNet: Deep Image Harmonization via Domain Verification", CVPR2020. Useful for imag…

Three methods of color transfer implemented in python.

Colour transfer algorithms for grading the colours of an image

[AAAI-2023] Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

[ECCV2024] Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors