High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network

2025-10-13

AI Summary

Existing photo enhancement methods struggle to balance accuracy and edge-deployment efficiency: high-accuracy models incur prohibitive computational overhead, while lightweight alternatives suffer from insufficient fidelity. This paper proposes LLF-LUT++, a lightweight and efficient framework for real-time enhancement of high-resolution images. Our approach addresses this trade-off through four key innovations: (1) a global-local collaborative architecture based on the Laplacian pyramid; (2) an image-adaptive 3D lookup table (LUT) with dual-weight fusion; (3) a spatial-frequency-aware Transformer for dynamic LUT weight prediction; and (4) localized Laplacian filtering to refine high-frequency details. Evaluated on the HDR+ dataset, LLF-LUT++ achieves a 2.64 dB PSNR improvement over prior work. It processes 4K images in just 13 ms on a single GPU—significantly outperforming state-of-the-art methods—while maintaining high accuracy, low latency, and strong feasibility for edge deployment.

Technology Category

• Computer Vision: Image and Video Retrieval
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Photo enhancement plays a crucial role in augmenting the visual aesthetics of a photograph. In recent years, photo enhancement methods have either focused on enhancement performance, producing powerful models that cannot be deployed on edge devices, or prioritized computational efficiency, resulting in inadequate performance for real-world applications. To this end, this paper introduces a pyramid network called LLF-LUT++, which integrates global and local operators through closed-form Laplacian pyramid decomposition and reconstruction. This approach enables fast processing of high-resolution images while also achieving excellent performance. Specifically, we utilize an image-adaptive 3D LUT that capitalizes on the global tonal characteristics of downsampled images, while incorporating two distinct weight fusion strategies to achieve coarse global image enhancement. To implement this strategy, we designed a spatial-frequency transformer weight predictor that effectively extracts the desired distinct weights by leveraging frequency features. Additionally, we apply local Laplacian filters to adaptively refine edge details in high-frequency components. After meticulously redesigning the network structure and transformer model, LLF-LUT++ not only achieves a 2.64 dB improvement in PSNR on the HDR+ dataset, but also further reduces runtime, with 4K resolution images processed in just 13 ms on a single GPU. Extensive experimental results on two benchmark datasets further show that the proposed approach performs favorably compared to state-of-the-art methods. The source code will be made publicly available at https://github.com/fengzhang427/LLF-LUT.

Problem

• Enhances high-resolution photos in real-time efficiently
• Balances computational speed with high-quality enhancement performance
• Integrates global tonal adjustment and local detail refinement

Innovation

• Laplacian pyramid network integrates global and local operators
• Image-adaptive 3D LUT with weight fusion strategies
• Spatial-frequency transformer predicts weights for enhancement