基于物理合成数据的稠密光照估计通用流程
A General Pipeline for Dense Illuminant Estimation via Physically Based Synthetic Data
浏览论文内容
中文总结 AI 辅助
本文提出一种基于物理3D渲染的通用流程，生成稠密光照标注的合成数据，用于预训练光照估计模型，在数据稀缺时单光照提升28%、多光照提升57%。
中文摘要 AI 辅助
光照估计是计算摄影中的一个基本问题，因为它能够校正由不同光照条件引起的颜色偏移。虽然基于学习的方法已展现出强大的性能，但其进展受到缺乏带有准确光照真值的大规模数据集的限制。在这项工作中，我们提出了一个通用且可复用的流程，从基于物理的3D渲染场景中导出稠密光照色度图。通过重新利用现有的3D场景集合，我们的方法能够在受控光照条件下系统地生成逐像素的光照标注，有效降低了基于学习的光照估计的数据获取门槛。利用该流程，我们生成了一个包含74,321张图像的大规模合成数据集，并将其用于预训练单光照和多光照估计模型。使用最先进架构的大量实验表明，合成预训练持续提升了性能，在数据稀缺情况下，单光照估计的提升高达28%，多光照估计的提升高达57%。这些发现表明，合成数据生成流程为光照估计方法的预训练提供了一种有效且可扩展的解决方案。
英文摘要
Illuminant estimation is a fundamental problem in computational photography, as it enables the correction of color shifts induced by varying lighting conditions. While learning-based methods have demonstrated strong performance, their progress is hindered by the limited availability of large-scale datasets with accurate illuminant ground-truth. In this work, we propose a general and reusable pipeline to derive dense illuminant chromaticity maps from physically based 3D-rendered scenes. By repurposing an existing 3D scene collection, our approach enables the systematic generation of pixel-wise illuminant annotations under controlled lighting conditions, effectively lowering the barrier to data acquisition for learning-based illuminant estimation. Using this pipeline, we generate a large-scale synthetic set of 74,321 images, which we employ for pre-training both single- and multi-illuminant estimation models. Extensive experiments with state-of-the-art architectures show that synthetic pre-training consistently improves performance, with gains of up to 28% for single-illuminant estimation and up to 57% for multi-illuminant estimation, particularly in data-scarce regimes. These findings demonstrate that synthetic data generation pipelines offer an effective and scalable solution for the pre-training of illuminant estimation methods.
发表机构
- University of Milano – Bicocca（米兰-比可卡大学）
机构由 AI 辅助整理，请以论文原文为准。
