UHD-processer: Unified UHD Image Restoration with Progressive Frequency Learning and Degradation-aware Prompts
Authors:
- 10 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 23121-23130
Abstract
We introduce UHD-Processor, a unified and robust framework for all-in-one image restoration, which is particularly resource-efficient for Ultra-High-Definition (UHD) images. To address the limitations of traditional all-in-one methods that rely on complex restoration backbones, our strategy employs a frequency domain decoupling progressive learning technique, motivated by curriculum learning, to incrementally learn restoration mappings from low to high frequencies. This approach incorporates specialized sub-network modules to effectively tackle different frequency bands in a divide-and-conquer manner, significantly enhancing the learning capability of simpler networks. Moreover, to accommodate the high-resolution characteristics of UHD images, we developed a variational autoencoder (VAE)-based framework that reduces computational complexity by modeling a concise latent space. It integrates task-specific degradation awareness in the encoder and frequency selection in the decoder, enhancing task comprehension and generalization. Our unified model is able to handle various degradations such as denoising, deblurring, dehazing, low-lighting, etc. Experimental evaluations extensively showcase the effectiveness of our dual-strategy approach, significantly improving UHD image restoration and achieving cutting-edge performance across diverse conditions. The code will be available at https://github.com/lyd-2022/UHD-processerKeywords
Funding Information
- National Natural Science Foundation of China
This publication has 30 references indexed in Scilit:
- When Fast Fourier Transform Meets Transformer for Image Restoration2024
- Restoring Images in Adverse Weather Conditions via Histogram Transformer2024
- GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather ConditionsInternational Journal of Computer Vision, 2024
- Fast Ultra High-Definition Video Deblurring via Multi-scale Separable NetworkInternational Journal of Computer Vision, 2023
- Stripformer: Strip Transformer for Fast Image Deblurring2022
- Visual Prompt Tuning2022
- RepVGG: Making VGG-style ConvNets Great Again2021
- High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks2020
- Training Behavior of Deep Neural Network in Frequency Domain2019
- Curriculum learning of multiple tasks2015