EDRC-NeRF: Enhanced Detail Recovery in Complex Lighting

Neural Radiation Field (NeRF) is a state-of-the-art 3D reconstruction paradigm that seamlessly combines neural networks with efficient volumetric rendering. However, it has limitations in accurately modeling light transmission variations and capturing fine geometric details under complex lighting conditions, which poses significant challenges for detail restoration. To address these issues, We propose EDRC-NeRF, a novel extension of Aleth-NeRF that inherits its volumetric rendering framework and network architecture. EDRC-NeRF further enhances detail recovery and model generalization in complex lighting scenarios. EDRC-NeRF utilizes a truncated cone sampling technique to efficiently mitigate excessive blurring and aliasing artifacts. In addition, it dynamically captures multi-view features to improve viewpoint synthesis quality and employs a pruning strategy to enhance model generalization under different lighting conditions. Experimental evaluations on the LOM and ROF datasets show that EDRC-NeRF provides a significant improvement in the quality of detail reproduction, verifying its robustness and excellent performance under complex lighting conditions.