Bright-NeRF:Brightening Neural Radiance Field with Color Restoration from Low-light Raw Images
This addresses the challenge of 3D scene reconstruction in low-light conditions for computer vision and graphics applications, representing an incremental improvement by adapting NeRF to handle raw image data with a new loss and dataset.
The paper tackles the problem of learning accurate scene representations from multi-view low-light raw images, which typically have noise and color distortion, by proposing Bright-NeRF, an unsupervised method that achieves color restoration, denoising, and enhanced novel view synthesis, significantly outperforming existing 2D and 3D approaches.
Neural Radiance Fields (NeRFs) have demonstrated prominent performance in novel view synthesis. However, their input heavily relies on image acquisition under normal light conditions, making it challenging to learn accurate scene representation in low-light environments where images typically exhibit significant noise and severe color distortion. To address these challenges, we propose a novel approach, Bright-NeRF, which learns enhanced and high-quality radiance fields from multi-view low-light raw images in an unsupervised manner. Our method simultaneously achieves color restoration, denoising, and enhanced novel view synthesis. Specifically, we leverage a physically-inspired model of the sensor's response to illumination and introduce a chromatic adaptation loss to constrain the learning of response, enabling consistent color perception of objects regardless of lighting conditions. We further utilize the raw data's properties to expose the scene's intensity automatically. Additionally, we have collected a multi-view low-light raw image dataset to advance research in this field. Experimental results demonstrate that our proposed method significantly outperforms existing 2D and 3D approaches. Our code and dataset will be made publicly available.