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

Learning scene flow from a monocular camera still remains a challenging taskdue to its ill-posedness as well as lack of annotated data. Self-supervisedmethods demonstrate learning scene flow estimation from unlabeled data, yettheir accuracy lags behind (semi-)supervised methods. In this paper, weintroduce a self-supervised monocular scene flow method that substantiallyimproves the accuracy over the previous approaches. Based on RAFT, astate-of-the-art optical flow model, we design a new decoder to iterativelyupdate 3D motion fields and disparity maps simultaneously. Furthermore, wepropose an enhanced upsampling layer and a disparity initialization technique,which overall further improves accuracy up to 7.2%. Our method achievesstate-of-the-art accuracy among all self-supervised monocular scene flowmethods, improving accuracy by 34.2%. Our fine-tuned model outperforms the bestprevious semi-supervised method with 228 times faster runtime. Code will bepublicly available.

RAFT-MSF: Self-Supervised Monocular Scene Flow using Recurrent Optimizer