Test- Time Adaptation for Depth Completion

Abstract

It is common to observe performance degradation when transferring models trained on some (source) datasets to tar-get testing data due to a domain gap between them. Existing methods for bridging this gap, such as domain adaptation (DA), may require the source data on which the model was trained (often not available), while others, i.e., source-free DA, require many passes through the testing data. We pro-pose an online test-time adaptation method for depth com-pletion, the task of inferring a dense depth map from a single image and associated sparse depth map, that closes the per-formance gap in a single pass. We first present a study on how the domain shift in each data modality affects model per-formance. Based on our observations that the sparse depth modality exhibits a much smaller covariate shift than the image, we design an embedding module trained in the source domain that preserves a mapping from features encoding only sparse depth to those encoding image and sparse depth. During test time, sparse depth features are projected using this map as a proxy for source domain features and are used as guidance to train a set of auxiliary parameters (i.e., adap-tation layer) to align image and sparse depth features from the target test domain to that of the source domain. We eval-uate our method on indoor and outdoor scenarios and show that it improves over baselines by an average of 21.1%. Code available at github.com/seobbroITTA-depth-completion.