PCDepth: Pattern-based Complementary Learning for Monocular Depth Estimation by Best of Both Worlds

arXiv:2402.18925v1 Announce Type: new
Abstract: Event cameras can record scene dynamics with high temporal resolution, providing rich scene details for monocular depth estimation (MDE) even at low-level illumination. Therefore, existing complementary learning approaches for MDE fuse intensity information from images and scene details from event data for better scene understanding. However, most methods directly fuse two modalities at pixel level, ignoring that the attractive complementarity mainly impacts high-level patterns that only occupy a few pixels. For example, event data is …

abstract arxiv best of cameras cs.cv data dynamics event images information intensity low mde temporal type