Geometry-Aware Unsupervised Domain Adaptation for Stereo Matching

03/26/2021
by   Hiroki Sakuma, et al.
0

Recently proposed DNN-based stereo matching methods that learn priors directly from data are known to suffer a drastic drop in accuracy in new environments. Although supervised approaches with ground truth disparity maps often work well, collecting them in each deployment environment is cumbersome and costly. For this reason, many unsupervised domain adaptation methods based on image-to-image translation have been proposed, but these methods do not preserve the geometric structure of a stereo image pair because the image-to-image translation is applied to each view separately. To address this problem, in this paper, we propose an attention mechanism that aggregates features in the left and right views, called Stereoscopic Cross Attention (SCA). Incorporating SCA to an image-to-image translation network makes it possible to preserve the geometric structure of a stereo image pair in the process of the image-to-image translation. We empirically demonstrate the effectiveness of the proposed unsupervised domain adaptation based on the image-to-image translation with SCA.

READ FULL TEXT

page 1

page 6

research
09/04/2023

StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation

We introduce a novel training strategy for stereo matching and optical f...
research
03/04/2019

Unsupervised Cross-spectral Stereo Matching by Learning to Synthesize

Unsupervised cross-spectral stereo matching aims at recovering disparity...
research
10/23/2019

Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptation

Image-to-image translation architectures may have limited effectiveness ...
research
05/05/2020

StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching

Large-scale synthetic datasets are beneficial to stereo matching but usu...
research
04/25/2018

Probabilistic Plant Modeling via Multi-View Image-to-Image Translation

This paper describes a method for inferring three-dimensional (3D) plant...
research
05/29/2019

Batch weight for domain adaptation with mass shift

Unsupervised domain transfer is the task of transferring or translating ...
research
12/16/2021

Improving Unsupervised Stain-To-Stain Translation using Self-Supervision and Meta-Learning

In digital pathology, many image analysis tasks are challenged by the ne...

Please sign up or login with your details

Forgot password? Click here to reset