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 scene understanding from point clouds plays a vital role for variousrobotic applications. Unfortunately, current state-of-the-art methods useseparate neural networks for different tasks like object detection or roomlayout estimation. Such a scheme has two limitations: 1) Storing and runningseveral networks for different tasks are expensive for typical roboticplatforms. 2) The intrinsic structure of separate outputs are ignored andpotentially violated. To this end, we propose the first transformerarchitecture that predicts 3D objects and layouts simultaneously, using pointcloud inputs. Unlike existing methods that either estimate layout keypoints oredges, we directly parameterize room layout as a set of quads. As such, theproposed architecture is termed as P(oint)Q(uad)-Transformer. Along with thenovel quad representation, we propose a tailored physical constraint lossfunction that discourages object-layout interference. The quantitative andqualitative evaluations on the public benchmark ScanNet show that the proposedPQ-Transformer succeeds to jointly parse 3D objects and layouts, running at aquasi-real-time (8.91 FPS) rate without efficiency-oriented optimization.Moreover, the new physical constraint loss can improve strong baselines, andthe F1-score of the room layout is significantly promoted from 37.9% to 57.9%.

PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds