Methods › Computer Vision › Point Cloud Models › PQ-Transformer

PointQuad-Transformer

PQ-Transformer

1 paper tagged archive 2025-07-28

Introduced by Xiaoxue Chen et al. in PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

PQ-Transformer, or PointQuad-Transformer, is a Transformer-based architecture that predicts 3D objects and layouts simultaneously, using point cloud inputs. Unlike existing methods that either estimate layout keypoints or edges, room layouts are directly parameterized as a set of quads. Along with the quad representation, a physical constraint loss function is used that discourages object-layout interference.

Given an input 3D point cloud of N points, the point cloud feature learning backbone extracts M context-aware point features of (3+C) dimensions, through sampling and grouping. A voting module and a farthest point sampling (FPS) module are used to generate K₁ object proposals and K₂ quad proposals respectively. Then the proposals are processed by a transformer decoder to further refine proposal features. Through several feedforward layers and non-maximum suppression (NMS), the proposals become the final object bounding boxes and layout quads.

PaperSource

Papers archive 2025-07-28

1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

4 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Object Detection1
Room Layout Estimation1
Scene Understanding1
object-detection1

Usage over time archive 2025-07-28

Papers per year tagged with PQ-Transformer: 2021 to 2021, peak 1 1 0 2021: 1 paper 2021
Papers per year the archive tags with this method, by the paper's archive date (1 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Point Cloud Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections