This letter proposes a self-supervised monocular image-to-depth prediction framework that is trained with an end-to-end photometric loss that handles not only $6-$DOF camera motion but also $6-$DOF moving object instances.… Click to show full abstract
This letter proposes a self-supervised monocular image-to-depth prediction framework that is trained with an end-to-end photometric loss that handles not only $6-$DOF camera motion but also $6-$DOF moving object instances. Self-supervision is performed by warping the images across a video sequence using depth and scene motion including object instances. One novelty of the proposed method is the use of the multi-head attention of the transformer network that matches moving objects across time and models their interaction and dynamics. This enables accurate and robust pose estimation for each object instance. Most image-to-depth predication frameworks make the assumption of rigid scenes, which largely degrades their performance with respect to dynamic objects. Only a few state-of-the-art (SOTA) papers have accounted for dynamic objects. The proposed method is shown to outperform these methods on standard benchmarks and the impact of the dynamic motion on these benchmarks is exposed. Furthermore, the proposed image-to-depth prediction framework is also shown to be competitive with SOTA video-to-depth prediction frameworks.
