English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose a novel method for reconstructing floor plans from noisy 3D pointclouds. Our main contribution is a principled approach that relies on the MonteCarlo Tree Search (MCTS) algorithm to maximize a suitable objective functionefficiently despite the complexity of the problem. Like previous work, we firstproject the input point cloud to a top view to create a density map and extractroom proposals from it. Our method selects and optimizes the polygonal shapesof these room proposals jointly to fit the density map and outputs an accuratevectorized floor map even for large complex scenes. To do this, we adaptedMCTS, an algorithm originally designed to learn to play games, to select theroom proposals by maximizing an objective function combining the fitness withthe density map as predicted by a deep network and regularizing terms on theroom shapes. We also introduce a refinement step to MCTS that adjusts the shapeof the room proposals. For this step, we propose a novel differentiable methodfor rendering the polygonal shapes of these proposals. We evaluate our methodon the recent and challenging Structured3D and Floor-SP datasets and show asignificant improvement over the state-of-the-art, without imposing any hardconstraints nor assumptions on the floor plan configurations.

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