Leveraging Intrinsic Components for Few-Shot Neural Radiance Fields in Unconstrained Illumination
Open Access
- 17 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 169150-169165
Abstract
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.Keywords
Funding Information
- Institute of Information and Communications Technology Planning and Evaluation (IITP) Grant funded by Korean Government through MSIT (RS-2023-00227592)
This publication has 47 references indexed in Scilit:
- Few-Shot NeRF by Adaptive Rendering Loss Regularization2024
- Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections2024
- SWAG: Splatting in the Wild Images with Appearance-Conditioned Gaussians2024
- FSGS: Real-Time Few-Shot View Synthesis Using Gaussian Splatting2024
- Recent advances in 3D Gaussian splattingComputational Visual Media, 2024
- SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image2022
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- Directional Illumination Estimation Sets and Multilevel Matching Metric for Illumination-Robust Face RecognitionIEEE Access, 2017
- Pixelwise View Selection for Unstructured Multi-View Stereo2016
- Large-Scale Data for Multiple-View StereopsisInternational Journal of Computer Vision, 2016