MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud
This addresses the challenge of 3D scene understanding from noisy data, though it appears incremental as it builds on existing methods like MCTS for scene understanding.
The paper tackles the problem of fitting cuboids to noisy 3D point clouds by introducing MonteBoxFinder, a discrete optimization algorithm that efficiently filters good cuboids from a dense initial set, resulting in improved efficiency and precision on the ScanNet dataset.
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.