AI Paper Atlas

Research map / Point clouds / Shape and surface completion

SLIBO-Net: Floorplan Reconstruction via Slicing Box Representation with Local Geometry Regularization

Jheng-Wei Su, Kuei-Yu Tung, Chi-Han Peng, Peter Wonka, Hung-Kuo Chu

NeurIPS 2023 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 1 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 Box IoU loss (ablation)SLIBO-Net box transformer · Structured3D testCorner F1: 0.765 -> 0.854Improved
add Box IoU loss (ablation)SLIBO-Net box transformer · Structured3D testAngle F1: 0.749 -> 0.844Improved
add Box IoU loss (ablation)SLIBO-Net box transformer · Structured3D testRoom F1: 0.972 -> 0.984Improved
add corner mask in corner loss (ablation)SLIBO-Net box transformer · Structured3D testCorner F1: 0.850 -> 0.854Improved
add corner mask in corner loss (ablation)SLIBO-Net box transformer · Structured3D testAngle F1: 0.84 -> 0.844Improved
add cell complex rounding in post-processing (ablation)SLIBO-Net · Structured3D testCorner F1: 0.745 -> 0.854Improved
add cell complex rounding in post-processing (ablation)SLIBO-Net · Structured3D testRoom F1: 0.963 -> 0.984Improved
add gap filling in post-processing (ablation)SLIBO-Net · Structured3D testCorner F1: 0.849 -> 0.854Improved
cluster slicing boxes with ground-truth room centers instead of predicted (ablation)SLIBO-Net · Structured3D testCorner F1: 0.854 -> 0.861Improved
increase box transformer tokens from 50 to 100 (ablation)SLIBO-Net · Structured3D testCorner F1: 0.854 -> 0.827Hurt
increase box transformer tokens from 50 to 300 (ablation)SLIBO-Net · Structured3D testCorner F1: 0.854 -> 0.789Hurt
increase box transformer tokens from 50 to 300 (ablation)SLIBO-Net · Structured3D testtraining time (sec./epoch): 38.36 -> 59.97Hurt

Later papers that compared with this method

2 later accepted papers report SLIBO-Net as a baseline in their results tables; 2 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