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

3D plane recovery from a single image can usually be divided into severalsubtasks of plane detection, segmentation, parameter estimation and possiblydepth estimation. Previous works tend to solve this task by either extendingthe RCNN-based segmentation network or the dense pixel embedding-basedclustering framework. However, none of them tried to integrate above relatedsubtasks into a unified framework but treat them separately and sequentially,which we suspect is potentially a main source of performance limitation forexisting approaches. Motivated by this finding and the success of query-basedlearning in enriching reasoning among semantic entities, in this paper, wepropose PlaneRecTR, a Transformer-based architecture, which for the first timeunifies all subtasks related to single-view plane recovery with a singlecompact model. Extensive quantitative and qualitative experiments demonstratethat our proposed unified learning achieves mutual benefits across subtasks,obtaining a new state-of-the-art performance on public ScanNet and NYUv2-Planedatasets. Codes are available at https://github.com/SJingjia/PlaneRecTR.

PlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View