AI Paper Atlas

Research map / Point clouds / Shape and surface completion

FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation

Honghao Xu, Juzhan Xu, Zeyu Huang, Pengfei Xu, Hui Huang, Ruizhen Hu

ECCV 2024 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 3 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 two-phase training (axis-aligned lines first, then diagonal) instead of optimizing all lines together (ablation)FRI-Net · Structured3D testCorner precision: 76.1 -> 90.8Improved
add wall-height map to density map in pre-processing (ablation)FRI-Net · Structured3D testCorner precision: 88.1 -> 90.8Improved
increase lines per type from 256 to 1024 (ablation)FRI-Net · Structured3D testCorner precision: 90.8 -> 86.9Hurt
increase lines from 256 to 512 (ablation)FRI-Net · Structured3D testCorner recall: 84.9 -> 85.2No clear effect
increase convex primitives from 64 to 128 (ablation)FRI-Net · Structured3D testCorner precision: 90.8 -> 91.1No clear effect
reduce convex primitives from 64 to 32 (ablation)FRI-Net · Structured3D testCorner precision: 90.8 -> 89.5Hurt
room-wise implicit representation instead of corner sequence predictionRoomFormer · Structured3D testAngle F1: 81.2 -> 86.9Improved
room-wise implicit representation under train-on-Structured3D, test-on-SceneCADRoomFormer · Structured3D to SceneCAD (cross-data)Corner F1: 60.3 -> 72.4Improved
FRI-Net versus RoomFormer on runtimeRoomFormer · Structured3D testruntime (s): 0.01 -> 0.09Hurt
add PolyDiffuse post-optimization to FRI-NetFRI-Net · Structured3D testCorner F1: 87.8 -> 91.1Improved
FRI-Net versus RoomFormer on corner recallRoomFormer · Structured3D testCorner recall: 85.3 vs 84.9No clear effect

Later papers that compared with this method

1 later accepted paper reports FRI-Net as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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