Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancement

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lou, Junyu, Zhao, Xiaorui, Shi, Kexuan, Gu, Shuhang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908452875403264
author Lou, Junyu
Zhao, Xiaorui
Shi, Kexuan
Gu, Shuhang
author_facet Lou, Junyu
Zhao, Xiaorui
Shi, Kexuan
Gu, Shuhang
contents Deep learning-based bilateral grid processing has emerged as a promising solution for image enhancement, inherently encoding spatial and intensity information while enabling efficient full-resolution processing through slicing operations. However, existing approaches are limited to linear affine transformations, hindering their ability to model complex color relationships. Meanwhile, while multi-layer perceptrons (MLPs) excel at non-linear mappings, traditional MLP-based methods employ globally shared parameters, which is hard to deal with localized variations. To overcome these dual challenges, we propose a Bilateral Grid-based Pixel-Adaptive Multi-layer Perceptron (BPAM) framework. Our approach synergizes the spatial modeling of bilateral grids with the non-linear capabilities of MLPs. Specifically, we generate bilateral grids containing MLP parameters, where each pixel dynamically retrieves its unique transformation parameters and obtain a distinct MLP for color mapping based on spatial coordinates and intensity values. In addition, we propose a novel grid decomposition strategy that categorizes MLP parameters into distinct types stored in separate subgrids. Multi-channel guidance maps are used to extract category-specific parameters from corresponding subgrids, ensuring effective utilization of color information during slicing while guiding precise parameter generation. Extensive experiments on public datasets demonstrate that our method outperforms state-of-the-art methods in performance while maintaining real-time processing capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12135
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancement
Lou, Junyu
Zhao, Xiaorui
Shi, Kexuan
Gu, Shuhang
Computer Vision and Pattern Recognition
Deep learning-based bilateral grid processing has emerged as a promising solution for image enhancement, inherently encoding spatial and intensity information while enabling efficient full-resolution processing through slicing operations. However, existing approaches are limited to linear affine transformations, hindering their ability to model complex color relationships. Meanwhile, while multi-layer perceptrons (MLPs) excel at non-linear mappings, traditional MLP-based methods employ globally shared parameters, which is hard to deal with localized variations. To overcome these dual challenges, we propose a Bilateral Grid-based Pixel-Adaptive Multi-layer Perceptron (BPAM) framework. Our approach synergizes the spatial modeling of bilateral grids with the non-linear capabilities of MLPs. Specifically, we generate bilateral grids containing MLP parameters, where each pixel dynamically retrieves its unique transformation parameters and obtain a distinct MLP for color mapping based on spatial coordinates and intensity values. In addition, we propose a novel grid decomposition strategy that categorizes MLP parameters into distinct types stored in separate subgrids. Multi-channel guidance maps are used to extract category-specific parameters from corresponding subgrids, ensuring effective utilization of color information during slicing while guiding precise parameter generation. Extensive experiments on public datasets demonstrate that our method outperforms state-of-the-art methods in performance while maintaining real-time processing capabilities.
title Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.12135