Toward Practical Monocular Indoor Depth Estimation
This work addresses the challenge of accurate depth estimation in cluttered indoor environments for applications like robotics and AR, though it is incremental as it builds on prior methods.
The authors tackled the problem of monocular depth estimation in complex indoor scenes, where existing methods fail, by proposing a structure distillation approach combined with left-right consistency learning, achieving real-time inference and improved performance in both simulation and real-world settings.
The majority of prior monocular depth estimation methods without groundtruth depth guidance focus on driving scenarios. We show that such methods generalize poorly to unseen complex indoor scenes, where objects are cluttered and arbitrarily arranged in the near field. To obtain more robustness, we propose a structure distillation approach to learn knacks from an off-the-shelf relative depth estimator that produces structured but metric-agnostic depth. By combining structure distillation with a branch that learns metrics from left-right consistency, we attain structured and metric depth for generic indoor scenes and make inferences in real-time. To facilitate learning and evaluation, we collect SimSIN, a dataset from simulation with thousands of environments, and UniSIN, a dataset that contains about 500 real scan sequences of generic indoor environments. We experiment in both sim-to-real and real-to-real settings, and show improvements, as well as in downstream applications using our depth maps. This work provides a full study, covering methods, data, and applications aspects.