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

Recently, records on stereo matching benchmarks are constantly broken byend-to-end disparity networks. However, the domain adaptation ability of thesedeep models is quite poor. Addressing such problem, we present a noveldomain-adaptive pipeline called AdaStereo that aims to align multi-levelrepresentations for deep stereo matching networks. Compared to previous methodsfor adaptive stereo matching, our AdaStereo realizes a more standard, completeand effective domain adaptation pipeline. Firstly, we propose a non-adversarialprogressive color transfer algorithm for input image-level alignment. Secondly,we design an efficient parameter-free cost normalization layer for internalfeature-level alignment. Lastly, a highly related auxiliary task,self-supervised occlusion-aware reconstruction is presented to narrow down thegaps in output space. Our AdaStereo models achieve state-of-the-artcross-domain performance on multiple stereo benchmarks, including KITTI,Middlebury, ETH3D, and DrivingStereo, even outperforming disparity networksfinetuned with target-domain ground-truths.

AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching