Fusion of stereo and still monocular depth estimates in a self-supervised learning context
We study how autonomous robots can learn by themselves to improve their depth estimation capability. In particular, we investigate a self-supervised learning setup in which stereo vision depth estimates serve as targets for a convolutional neural network (CNN) that transforms a single still image to a dense depth map. After training, the stereo and mono estimates are fused with a novel fusion method that preserves high confidence stereo estimates, while leveraging the CNN estimates in the low-confidence regions. The main contribution of the article is that it is shown that the fused estimates lead to a higher performance than the stereo vision estimates alone. Experiments are performed on the KITTI dataset, and on board of a Parrot SLAMDunk, showing that even rather limited CNNs can help provide stereo vision equipped robots with more reliable depth maps for autonomous navigation.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous NavigationDepth EstimationSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation
Current self-supervised depth estimation algorithms mainly focus on either stereo or monocular only, neglecting the reciprocal relations between them. In this paper, we propose a simple yet effective framework to imp…
Depth EstimationMonocular Depth EstimationStereo MatchingStereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space
We introduce StereoSpace, a diffusion-based framework for monocular-to-stereo synthesis that models geometry purely through viewpoint conditioning, without explicit depth or warping. A canonical rectified space and the c…
Sdf-GAN: Semi-supervised Depth Fusion with Multi-scale Adversarial Networks
Refining raw disparity maps from different algorithms to exploit their complementary advantages is still challenging. Uncertainty estimation and complex disparity relationships among pixels limit the accuracy and robustn…
Setting-1/2Learning Monocular Depth Estimation via Selective Distillation of Stereo Knowledge
Monocular depth estimation has been extensively explored based on deep learning, yet its accuracy and generalization ability still lag far behind the stereo-based methods. To tackle this, a few recent studies have propos…
DecoderDepth EstimationMonocular Depth EstimationDiving into the Fusion of Monocular Priors for Generalized Stereo Matching
The matching formulation makes it naturally hard for the stereo matching to handle ill-posed regions like occlusions and non-Lambertian surfaces. Fusing monocular priors has been proven helpful for ill-posed matching, bu…
Stereo Matching