RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion

arXiv:2306.03584v2 Announce Type: replace
Abstract: Raw depth images captured in indoor scenarios frequently exhibit extensive missing values due to the inherent limitations of the sensors and environments. For example, transparent materials frequently elude detection by depth sensors; surfaces may introduce measurement inaccuracies due to their polished textures, extended distances, and oblique incidence angles from the sensor. The presence of incomplete depth maps imposes significant challenges for subsequent vision applications, prompting the development of numerous depth completion techniques to mitigate this …

abstract arxiv cs.ai cs.cv cyclegan detection environments example fusion gan images limitations materials measurement missing values raw sensors transparent type values