MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud

TL;DR

MonteBoxFinder is a novel stochastic optimization method that efficiently filters and fits cuboids to noisy 3D point clouds, improving scene understanding accuracy.

Contribution

It introduces a discrete optimization algorithm based on MCTS for filtering cuboids in noisy point clouds, enhancing efficiency and precision over existing methods.

Findings

More efficient than baseline methods

Achieves higher accuracy in cuboid fitting

Demonstrated on ScanNet dataset

Abstract

We present MonteBoxFinder, a method that, given a noisy input point cloud, fits cuboids to the input scene. Our primary contribution is a discrete optimization algorithm that, from a dense set of initially detected cuboids, is able to efficiently filter good boxes from the noisy ones. Inspired by recent applications of MCTS to scene understanding problems, we develop a stochastic algorithm that is, by design, more efficient for our task. Indeed, the quality of a fit for a cuboid arrangement is invariant to the order in which the cuboids are added into the scene. We develop several search baselines for our problem and demonstrate, on the ScanNet dataset, that our approach is more efficient and precise. Finally, we strongly believe that our core algorithm is very general and that it could be extended to many other problems in 3D scene understanding.