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

Hanjiang Hu, Lingdong Kong, Shaoyuan Xie, Lai Ng, Benoit Cottereau, Wei Ooi

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 74 functions out of this paper's own repositories and ran 57 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Showing the first 60. An agent gets every one from get_harvested_code_for_paper("2310.15171").

Repositories linked to this paper

• ldkong1205/robodepth — marked official in Papers with Code; named in the paper
• SenZHANG-GitHub/ekf-imu-depth
• TJ-IPLab/DNet
• brandleyzhou/DIFFNet
• cleinc/bts
• hyBlue/FSRE-Depth
• isl-org/DPT
• kamiLight/CADepth-master
• ldkong1205/RoboDepth
• naoto0804/pytorch-AdaIN
• nianticlabs/depth-hints
• nianticlabs/manydepth
• nianticlabs/monodepth2
• noahzn/Lite-Mono
• rgeirhos/Stylized-ImageNet
• schelv/monodepth2
• shariqfarooq123/AdaBins
• xingyuuchen/tri-depth

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.15171")
get_code_for_paper("2310.15171")
have("2310.15171")

Connect an agent — have() is free.