Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalization

2023/12/14 by Luca Bartolomei, Bartolomei, Luca, Matteo Poggi +7 · 3 citations
Computer Science · Engineering · #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #Optical Coherence Tomography Applications

paper · pdf · doi:10.48550/arxiv.2312.09254

openalex publication_date 2023/12/14 · openalex created_date 2023/12/16 · openalex updated_date 2026/07/28

Abstract

This paper proposes a new framework for depth completion robust against domain-shifting issues. It exploits the generalization capability of modern stereo networks to face depth completion, by processing fictitious stereo pairs obtained through a virtual pattern projection paradigm. Any stereo network or traditional stereo matcher can be seamlessly plugged into our framework, allowing for the deployment of a virtual stereo setup that is future-proof against advancement in the stereo field. Exhaustive experiments on cross-domain generalization support our claims. Hence, we argue that our framework can help depth completion to reach new deployment scenarios.

Cited by

• SPADE: Sparsity Adaptive Depth Estimator for Zero-Shot, Real-Time, Monocular Depth Estimation in Underwater Environments
• Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion
• PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency

Related

• Achieving Domain Robustness in Stereo Matching Networks by Removing Shortcut Learning
• Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective
• Matching-space Stereo Networks for Cross-domain Generalization
• Reversing the cycle: self-supervised deep stereo through enhanced\n monocular distillation
• GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature