Learning Relighting and Intrinsic Decomposition in Neural Radiance Fields

Autor:	Yang, Yixiong, Hu, Shilin, Wu, Haoyu, Baldrich, Ramon, Samaras, Dimitris, Vanrell, Maria
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	The task of extracting intrinsic components, such as reflectance and shading, from neural radiance fields is of growing interest. However, current methods largely focus on synthetic scenes and isolated objects, overlooking the complexities of real scenes with backgrounds. To address this gap, our research introduces a method that combines relighting with intrinsic decomposition. By leveraging light variations in scenes to generate pseudo labels, our method provides guidance for intrinsic decomposition without requiring ground truth data. Our method, grounded in physical constraints, ensures robustness across diverse scene types and reduces the reliance on pre-trained models or hand-crafted priors. We validate our method on both synthetic and real-world datasets, achieving convincing results. Furthermore, the applicability of our method to image editing tasks demonstrates promising outcomes. Comment: Accepted by CVPR 2024 Workshop Neural Rendering Intelligence(NRI)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2406.11077 Zobrazit plný text záznamu View this record from Arxiv