RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

• Main Authors: Kong, Lingdong, Xie, Shaoyuan, Hu, Hanjiang, Ng, Lai Xing, Cottereau, Benoit R, Ooi, Wei Tsang
• Format: Journal Article
• Language: English
• Published: 23-10-2023
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Computer Science - Robotics
• DOI: 10.48550/arxiv.2310.15171

Depth estimation from monocular images is pivotal for real-world visual
perception systems. While current learning-based depth estimation models train
and test on meticulously curated data, they often overlook out-of-distribution
(OoD) situations. Yet, in practical settings -- especially safety-critical ones
like autonomous driving -- common corruptions can arise. Addressing this
oversight, we introduce a comprehensive robustness test suite, RoboDepth,
encompassing 18 corruptions spanning three categories: i) weather and lighting
conditions; ii) sensor failures and movement; and iii) data processing
anomalies. We subsequently benchmark 42 depth estimation models across indoor
and outdoor scenes to assess their resilience to these corruptions. Our
findings underscore that, in the absence of a dedicated robustness evaluation
framework, many leading depth estimation models may be susceptible to typical
corruptions. We delve into design considerations for crafting more robust depth
estimation models, touching upon pre-training, augmentation, modality, model
capacity, and learning paradigms. We anticipate our benchmark will establish a
foundational platform for advancing robust OoD depth estimation.