AI Paper Atlas

Research map / Point clouds / Point cloud classification

PolyRoom: Room-aware Transformer for Floorplan Reconstruction

Yuzhou Liu, Lingjie Zhu, Xiaodong Ma, Hanqiao Ye, Xiang Gao, Xianwei Zheng, Shuhan Shen

ECCV 2024 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add uniform sampling floorplan representation (ablation)PolyRoom · Structured3D testCorner precision: 78.2 -> 94.6Improved
add room-aware query initialization from instance segmentation (ablation)PolyRoom · Structured3D testCorner precision: 89.3 -> 94.6Improved
replace vanilla self-attention with room-aware self-attention (ablation)PolyRoom · Structured3D testCorner precision: 94.1 -> 94.6Improved
room-aware self-attention instead of vanilla (ablation)PolyRoom · Structured3D testGPU memory: 18707M -> 11957MImproved
add vertex selection (ablation)PolyRoom · Structured3D testCorner precision: 81.4 -> 94.6Improved
add angle loss (ablation)PolyRoom · Structured3D testAngle precision: 85.0 -> 89.3Improved
add polygonization in vertex selection (ablation)PolyRoom · Structured3D testCorner precision: 92.6 -> 94.6Improved
combine intra-room and inter-room attention rather than either alone (ablation)PolyRoom · Structured3D testCorner precision: 93.3 -> 94.6Improved
increase vertex number from 40 to 50 (ablation)PolyRoom · Structured3D testCorner precision: 94.6 -> 94.4Hurt
increase decoder layers from 6 to 8 (ablation)PolyRoom · Structured3D testRoom precision: 98.9 -> 98.7No clear effect
use stronger instance segmentation network for initialization (ablation)PolyRoom · Structured3D testCorner precision: 92.6 -> 94.6Improved
use PolyRoom instead of RoomFormer in cross-dataset transferPolyRoom · Structured3D to SceneCADCorner F1: 60.3 -> 78.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy