paper-with-me

홈 › Papers

RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement

2026-05-05 · Yucheng Xin, Wu Chen, Xiang Chen, Guangwei Gao, Xinchun Wang, Ruize Wu, Dianjie Lu, Guijuan Zhang, Linwei Fan, Zhuoran Zheng arxiv

To address module fragmentation, uninterpretable mappings, and deployment constraints in RAW-domain demosaicing, color correction, and detail enhancement, this paper proposes RPBA-Net, an interpretable residual pyramid bilateral affine network for RAW-domain ISP enhancement. Given packed RAW as input, the method performs residual affine base reconstruction by estimating a base RGB representation and learning identity-guided residual affine corrections, thereby unifying demosaicing and enhancement. It further builds pyramid bilateral affine grids and combines guide-driven autoregressive adaptive slicing with adaptive cross-layer fusion to hierarchically model global tone restoration and local texture enhancement. In addition, smoothness, cross-scale consistency, and magnitude regularization terms are introduced to improve model stability, controllability, and structural interpretability. Extensive experiments demonstrate that RPBA-Net surpasses representative RAW-to-sRGB methods and achieves state-of-the-art performance in reconstruction fidelity and perceptual quality, while maintaining low model complexity and strong deployment potential for mobile and embedded platforms.

📄 PDF Abstract BibTeX arXiv:2605.03626

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence

2018-07-09 · ECCV 2018 9 · Sangryul Jeon, Seungryong Kim, Dongbo Min, Kwanghoon Sohn

This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images. To deal with intra…

regressionSemantic correspondence

LogicPrpBank: A Corpus for Logical Implication and Equivalence

2024-02-14 · Zhexiong Liu, Jing Zhang, Jiaying Lu, Wenjing Ma 외

Logic reasoning has been critically needed in problem-solving and decision-making. Although Language Models (LMs) have demonstrated capabilities of handling multiple reasoning tasks (e.g., commonsense reasoning), their a…

Decision Making

Hist2Style: Histogram-Guided Stylization with Bilateral Grids

2026-06-01 · Dekel Galor, Adam Pikielny, Zhoutong Zhang, Ke Wang 외 arxiv

Photorealistic style transfer aims to match the color and tone of an input image to that of a style target while preserving the content and details of the original scene. Although existing large image models can facilita…

Style TransferImage Editing

Deep Bilateral Learning for Real-Time Image Enhancement

2017-07-10 · Michaël Gharbi, Jiawen Chen, Jonathan T. Barron, Samuel W. Hasinoff 외

Performance is a critical challenge in mobile image processing. Given a reference imaging pipeline, or even human-adjusted pairs of images, we seek to reproduce the enhancements and enable real-time evaluation. For this,…

Image EnhancementImage Retouching

LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing

2026-05-12 · Yongcong Wang, Chengchao Shen, Guangwei Gao, Wei Wang 외 arxiv

Currently, there is a gap in the field of ultra-high-definition (UHD) video dehazing due to the lack of a benchmark for evaluation. Furthermore, existing video dehazing methods cannot run on consumer-grade GPUs when proc…