Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalization
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.
Code (1)
Tasks
Depth CompletionDomain GeneralizationStereo MatchingSimilar Papers 제목 키워드 기반
Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers
Stereo depth estimation relies on optimal correspondence matching between pixels on epipolar lines in the left and right images to infer depth. In this work, we revisit the problem from a sequence-to-sequence corresponde…
Depth EstimationPositionStereo Depth EstimationNon-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matching
We propose a non-learning depth completion method for a sparse depth map captured using a light detection and ranging (LiDAR) sensor guided by a pair of stereo images. Generally, conventional stereo-aided depth completio…
Camera CalibrationDepth CompletionDepth EstimationStereo Matching3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization
The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the Li-DAR sensor and stereo camera for improved depth perception. Instead of directly fusing estimated depths acros…
Depth CompletionStereo-LiDAR FusionStereo MatchingStereo Matching HandTemporally Consistent Stereo Matching
Stereo matching provides depth estimation from binocular images for downstream applications. These applications mostly take video streams as input and require temporally consistent depth maps. However, existing methods m…
Depth EstimationStereo MatchingNoise-Aware Unsupervised Deep Lidar-Stereo Fusion
In this paper, we present LidarStereoNet, the first unsupervised Lidar-stereo fusion network, which can be trained in an end-to-end manner without the need of ground truth depth maps. By introducing a novel "Feedback Loo…
3D geometryDepth CompletionStereo MatchingStereo Matching Hand