Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement

2026-02-28

AI Summary

This work addresses the challenge of efficiently restoring ultra-high-definition (UHD) images degraded by low-light conditions, haze, and blur. To this end, the authors propose UHDPromer, a novel method that introduces neural discriminative priors (NDP) to model the discrepancy between high- and low-resolution features for the first time. UHDPromer incorporates a discriminative prompt attention (NDPA) mechanism and a discriminative prompt network (NDPN) to enable discriminative information-driven feature selection and enhancement. Built upon a Transformer architecture and augmented with a super-resolution-guided reconstruction strategy, UHDPromer achieves state-of-the-art performance across three UHD restoration tasks while maintaining superior computational efficiency.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

We propose a simple yet effective UHDPromer, a neural discrimination-prompted Transformer, for Ultra-High-Definition (UHD) image restoration and enhancement. Our UHDPromer is inspired by an interesting observation that there implicitly exist neural differences between high-resolution and low-resolution features, and exploring such differences can facilitate low-resolution feature representation. To this end, we first introduce Neural Discrimination Priors (NDP) to measure the differences and then integrate NDP into the proposed Neural Discrimination-Prompted Attention (NDPA) and Neural Discrimination-Prompted Network (NDPN). The proposed NDPA re-formulates the attention by incorporating NDP to globally perceive useful discrimination information, while the NDPN explores a continuous gating mechanism guided by NDP to selectively permit the passage of beneficial content. To enhance the quality of restored images, we propose a super-resolution-guided reconstruction approach, which is guided by super-resolving low-resolution features to facilitate final UHD image restoration. Experiments show that UHDPromer achieves the best computational efficiency while still maintaining state-of-the-art performance on $3$ UHD image restoration and enhancement tasks, including low-light image enhancement, image dehazing, and image deblurring. The source codes and pre-trained models will be made available at https://github.com/supersupercong/uhdpromer.

Problem

• UHD image restoration
• image enhancement
• low-light enhancement
• image dehazing
• image deblurring

Innovation

• Neural Discrimination Priors
• Prompted Transformer
• UHD Image Restoration
• Attention Mechanism
• Super-Resolution-Guided Reconstruction