Self-Supervised Monocular Depth Estimation in Challenging Environments Based on Illumination Compensation PoseNet

Self-supervised depth estimation has attracted much attention due to its ability to improve the 3D perception capabilities of unmanned systems. However, existing unsuper- vised frameworks rely on the assumption of photometric con- sistency, which may not hold in challenging environments such as night-time, rainy nights, or snowy winters due to complex lighting and reflections, resulting in inconsistent photometry across different frames for the same pixel. To address this prob- lem, we propose a self-supervised monocular depth estimation unified framework that can handle these complex scenarios, which has the following characteristics: (1) an Illumination Compensation PoseNet (ICP) is designed, which is based on the classic Phong illumination theory and compensates for lighting changes in adjacent frames by estimating per-pixel transformations; (2) a Dual-Axis Transformer (DAT) block is proposed as the backbone network of the depth encoder, which infers the depth of local repeat-texture areas through spatial-channel dual-dimensional global context information of images. Experimental results demonstrate that our approach achieves state-of-the-art depth estimation results in complex environments on the challenging Oxford RobotCar dataset.