English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Stereo-matching is a fundamental problem in computer vision. Despite recentprogress by deep learning, improving the robustness is ineluctable whendeploying stereo-matching models to real-world applications. Different from thecommon practices, i.e., developing an elaborate model to achieve robustness, weargue that collecting multiple available datasets for training is a cheaper wayto increase generalization ability. Specifically, this report presents animproved RaftStereo trained with a mixed dataset of seven public datasets forthe robust vision challenge (denoted as iRaftStereo_RVC). When evaluated on thetraining sets of Middlebury, KITTI-2015, and ETH3D, the model outperforms itscounterparts trained with only one dataset, such as the popular Sceneflow.After fine-tuning the pre-trained model on the three datasets of the challenge,it ranks at 2nd place on the stereo leaderboard, demonstrating the benefits ofmixed dataset pre-training.

An Improved RaftStereo Trained with A Mixed Dataset for the Robust Vision Challenge 2022