H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry

04/22/2021
by   Baoru Huang, et al.
16

Depth estimation from a stereo image pair has become one of the most explored applications in computer vision, with most of the previous methods relying on fully supervised learning settings. However, due to the difficulty in acquiring accurate and scalable ground truth data, the training of fully supervised methods is challenging. As an alternative, self-supervised methods are becoming more popular to mitigate this challenge. In this paper, we introduce the H-Net, a deep-learning framework for unsupervised stereo depth estimation that leverages epipolar geometry to refine stereo matching. For the first time, a Siamese autoencoder architecture is used for depth estimation which allows mutual information between the rectified stereo images to be extracted. To enforce the epipolar constraint, the mutual epipolar attention mechanism has been designed which gives more emphasis to correspondences of features which lie on the same epipolar line while learning mutual information between the input stereo pair. Stereo correspondences are further enhanced by incorporating semantic information to the proposed attention mechanism. More specifically, the optimal transport algorithm is used to suppress attention and eliminate outliers in areas not visible in both cameras. Extensive experiments on KITTI2015 and Cityscapes show that our method outperforms the state-ofthe-art unsupervised stereo depth estimation methods while closing the gap with the fully supervised approaches.

READ FULL TEXT

page 3

page 4

page 7

page 8

research
05/17/2017

Self-Supervised Siamese Learning on Stereo Image Pairs for Depth Estimation in Robotic Surgery

Robotic surgery has become a powerful tool for performing minimally inva...
research
07/09/2021

Self-Supervised Generative Adversarial Network for Depth Estimation in Laparoscopic Images

Dense depth estimation and 3D reconstruction of a surgical scene are cru...
research
08/17/2022

Self-Supervised Depth Estimation in Laparoscopic Image using 3D Geometric Consistency

Depth estimation is a crucial step for image-guided intervention in robo...
research
04/18/2020

On the Synergies between Machine Learning and Stereo: a Survey

Stereo matching is one of the longest-standing problems in computer visi...
research
09/13/2021

On the Sins of Image Synthesis Loss for Self-supervised Depth Estimation

Scene depth estimation from stereo and monocular imagery is critical for...
research
09/17/2019

Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled Networks

Recent deep monocular depth estimation approaches based on supervised re...
research
11/11/2019

360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume

Recently, end-to-end trainable deep neural networks have significantly i...

Please sign up or login with your details

Forgot password? Click here to reset