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

TL;DR

This paper introduces MonteFloor, a novel approach that extends Monte Carlo Tree Search to accurately reconstruct large-scale floor plans from noisy 3D point clouds, achieving significant improvements over existing methods.

Contribution

The paper presents a new MCTS-based method for joint optimization of room proposals, including a differentiable shape refinement, for accurate large-scale floor plan reconstruction.

Findings

Significant improvement over state-of-the-art on Structured3D and Floor-SP datasets

Effective joint optimization of room proposals using MCTS

A novel differentiable rendering method for polygonal shapes

Abstract

We propose a novel method for reconstructing floor plans from noisy 3D point clouds. Our main contribution is a principled approach that relies on the Monte Carlo Tree Search (MCTS) algorithm to maximize a suitable objective function efficiently despite the complexity of the problem. Like previous work, we first project the input point cloud to a top view to create a density map and extract room proposals from it. Our method selects and optimizes the polygonal shapes of these room proposals jointly to fit the density map and outputs an accurate vectorized floor map even for large complex scenes. To do this, we adapted MCTS, an algorithm originally designed to learn to play games, to select the room proposals by maximizing an objective function combining the fitness with the density map as predicted by a deep network and regularizing terms on the room shapes. We also introduce a refinement step to MCTS that adjusts the shape of the room proposals. For this step, we propose a novel differentiable method for rendering the polygonal shapes of these proposals. We evaluate our method on the recent and challenging Structured3D and Floor-SP datasets and show a significant improvement over the state-of-the-art, without imposing any hard constraints nor assumptions on the floor plan configurations.