Do More With What You Have: Transferring Depth-Scale from Labeled to Unlabeled Domains

arXiv:2303.07662v3 Announce Type: replace
Abstract: Transferring the absolute depth prediction capabilities of an estimator to a new domain is a task with significant real-world applications. This task is specifically challenging when images from the new domain are collected without ground-truth depth measurements, and possibly with sensors of different intrinsics. To overcome such limitations, a recent zero-shot solution was trained on an extensive training dataset and encoded the various camera intrinsics. Other solutions generated synthetic data with depth labels that matched …

abstract applications arxiv capabilities cs.cv domain domains eess.iv estimator ground-truth images prediction scale sensors truth type world