AI Paper Atlas

Research map / Point clouds / Shape and surface completion

MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans

Sinisa Stekovic, Mahdi Rad, Friedrich Fraundorfer, Vincent Lepetit

ICCV 2021 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 43 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 the refinement step (ablation)MonteFloor · Structured3DMA precision / recall: 0.82 -> 0.90 precision, 0.75 -> 0.82 recallImproved
add the refinement step (ablation)MonteFloor · Structured3DAngle precision: 0.65 -> 0.86Improved
add the refinement step (ablation)MonteFloor · Structured3Dcomputation time (s): 12 ± 8 -> 71 ± 40Hurt
add angle regularization L_ang (ablation)MonteFloor · Structured3DAngle precision: 0.73 -> 0.86Improved
add angle regularization L_ang (ablation)MonteFloor · Structured3DAngle recall: 0.68 -> 0.75Improved
add global contact regularization L_glob (ablation)MonteFloor · Structured3DRoom precision: 0.85 -> 0.96Improved
add global contact regularization L_glob (ablation)MonteFloor · Structured3DCorner precision: 0.78 -> 0.89Improved
add drift regularization L_0 (ablation)MonteFloor · Structured3DMA precision: 0.88 -> 0.90Improved
add drift regularization L_0 (ablation)MonteFloor · Structured3DRoom precision: 0.92 -> 0.96Improved
add the learned metric network f (ablation)MonteFloor · Structured3DMA recall: 0.17 -> 0.82Improved
replace Floor-SP with MonteFloor (MCTS selection and refinement)floor plan reconstruction · Structured3DMA precision / recall: 0.83 -> 0.90 precision, 0.78 -> 0.82 recallImproved
replace Floor-SP with MonteFloor, metric network trained only on Structured3Dfloor plan reconstruction · Floor-SP test setMA precision / recall: 0.74 -> 0.78 precision, 0.64 -> 0.67 recallImproved

Later papers that compared with this method

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

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