Leveraging Intrinsic Components for Few-shot Neural Radiance Fields in Unconstrained Illumination

Neural Radiance Fields (NeRF) has demonstrated its efficacy in synthesizing novel view images, and has yielded promising outcomes under specific conditions: 1) dense, multi-view observations, 2) constrained illumination across input views, and 3) known camera poses. In real-world scenarios, however, these conditions are rarely satisfied. Especially when confronted with a limited number of input views and varying illumination conditions, NeRF experiences diminished performance. While some of the previous works have addressed novel view synthesis under unconstrained illumination, their effectiveness still hinges on dense observations. In this paper, we tackle the challenge of few-shot NeRF under unconstrained illumination by leveraging illumination-invariant intrinsic components to provide stronger cross-view regularization. To further enhance practicality, we design a lightweight extension that achieves comparable improvements with minimal computational overhead. We also establish new benchmarks featuring diverse viewpoints and illumination conditions, and demonstrate through extensive experiments that our framework consistently improves robustness and synthesis quality in real-world settings.