Progressive Camera-LiDAR Adaptation for Scene Flow Estimation

3D scene flow aims to recover the dense geometry and 3D motion of dynamic scenes. This paper explores the transformation and adaptation of the 2D-3D feature space in the joint estimation of optical flow and scene flow. Our key insight is to fully leverage the unique characteristics of each modality and maximize their inter-modality complementarity. To achieve this, we propose a novel architecture, named PAFlow, which consists of Camera-LiDAR Adaptation and Spatial Characteristics Adaptation. PAFlow achieves an error of 4.23% on real-world KITTI Scene Flow benchmark, with significantly fewer parameters compared to previous methods. This study will support dynamic scene understanding for the geospatial community.