针对夜景渲染的视觉失真与色彩偏差，提出新方法提升真实感。
Beyond Pixel Fidelity: Minimizing Perceptual Distortion and Color Bias in Night Photography Rendering
- 基于HVI色彩空间，融合小波特征传播与RAW域处理，减少细节丢失。
- 在NTIRE 2025数据集上，颜色差异（CIE2000）和感知相似度（LPIPS）达新高。
- 适合关注夜景图像真实感与色彩准确性的计算机视觉研究者。
夜景渲染（NPR）因场景中暗区与强光源并存导致极端明暗对比，面临巨大挑战。现有方法主要优化像素保真度，却存在显著感知差距，常损害视觉质量。本文提出pHVI-ISPNet，一种基于稳健HVI色彩空间的RAW-to-RGB框架。网络集成四项关键改进：RAW域特征处理与基于小波的特征传播以缓解高频细节丢失；基于样本的动态损失系数确保不同曝光水平下训练稳定；基于特征分布的损失项保障严格的色彩恒常性。在NTIRE 2025挑战赛引入的数据集上评估显示，该方法在保持竞争力保真度的同时，在CIE2000颜色差与LPIPS指标上达到新最优结果，验证了其感知驱动设计在高质量夜景成像中的有效性。
原文摘要 · Abstract (English)
Night Photography Rendering (NPR) poses a significant challenge due to the extreme contrast between dark and illuminated areas in scenes, stemming from concurrent capture of severely dark regions alongside intense point light sources. Existing methods, which are mainly tailored for fidelity metrics, reveal considerable perceptual gaps and often detract from visual quality. We introduce pHVI-ISPNet, a novel RAW-to-RGB framework built on the robust HVI color space. Our network integrates four distinct key refinements: RAW-domain feature processing and Wavelet-based feature propagation to mitigate high-frequency detail loss; sample-based dynamic loss coefficients to ensure stable learning across varying exposure levels; and loss term based on feature distributions to maintain rigorous color constancy. Evaluations on the dataset introduced in the NTIRE 2025 challenge on NPR confirm our approach achieves competitive fidelity while establishing new state-of-the-art results in both CIE2000 color difference and LPIPS. This validates our perceptually-driven design for high-quality nighttime imaging.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。