Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-based Autonomous Driving

arXiv:2402.15583v1 Announce Type: cross
Abstract: Due to the lack of depth cues in images, multi-frame inputs are important for the success of vision-based perception, prediction, and planning in autonomous driving. Observations from different angles enable the recovery of 3D object states from 2D image inputs if we can identify the same instance in different input frames. However, the dynamic nature of autonomous driving scenes leads to significant changes in the appearance and shape of each instance captured by the camera …

2d image 3d object abstract arxiv autonomous autonomous driving cs.cv cs.lg driving image images inputs perception planning prediction recovery representation representation learning success temporal type unsupervised vision