Relative Illumination Fields: Learning Medium and Light Independent Underwater Scenes
This addresses the problem of underwater scene reconstruction for robotics in deep, poorly-lit environments, representing an incremental advance over existing homogeneous illumination methods.
The paper tackles the problem of constructing consistent Neural Radiance Fields in underwater scenes with uneven, dynamic illumination, proposing a method that combines an illumination field attached to the camera with a volumetric medium representation. Results demonstrate effectiveness and flexibility in handling such challenging environments.
We address the challenge of constructing a consistent and photorealistic Neural Radiance Field in inhomogeneously illuminated, scattering environments with unknown, co-moving light sources. While most existing works on underwater scene representation focus on a static homogeneous illumination, limited attention has been paid to scenarios such as when a robot explores water deeper than a few tens of meters, where sunlight becomes insufficient. To address this, we propose a novel illumination field locally attached to the camera, enabling the capture of uneven lighting effects within the viewing frustum. We combine this with a volumetric medium representation to an overall method that effectively handles interaction between dynamic illumination field and static scattering medium. Evaluation results demonstrate the effectiveness and flexibility of our approach.