Long Presentation
in
Affinity Workshop: LXAI Research @ NeurIPS 2020
Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes
Juan Luis GonzalezBello
Self-supervised depth estimators have shown results comparable to the supervised methods on the challenging Single Image Depth Estimation task by exploiting relations between target and reference views in the data. However, previous works have not effectively neglected occlusions between the target and the reference images and rely on rigid photometric assumptions or on the SIDE network to infer depth and occlusions, resulting in limited performance. In this paper, we propose a method to “Forget About the LiDAR” (FAL), with Mirrored Exponential Disparity (MED) probability volumes for the training of monocular depth estimators from stereo images. Our MED representation allows us to obtain geometrically inspired occlusion maps with our novel Mirrored Occlusion Module (MOM), which does not impose a learning burden on our FAL-net. Our FAL-net is remarkably light-weight and outperforms the previous state-of-the-art methods with 8x fewer parameters and 3x faster inference speeds on KITTI.