MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud
Michaël Ramamonjisoa1, Sinisa Stekovic2 and Vincent Lepetit1,2
1LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS,
2 Institute for Computer Graphics and Vision, Graz University of Technology
ECCV 2022
[Paper]
[Code]

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.

Method

 [GitHub]

Paper and Supplementary Material

Michaël Ramamonjisoa1, Sinisa Stekovic2 and Vincent Lepetit1,2
MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud
In European Conference on Computer Vision (ECCV)

Citation

Please consider citing our paper if you found it helpful for your projects: 
@article{ramamonjisoa2022mbf, 
 Title = {MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud}, 
 Author = {M. Ramamonjisoa, S. Stekovic and V. Lepetit}, 
 Journal = {European Conference on Computer Vision (ECCV)}, 
 Year = {2022}
 }

Acknowledgements

This webpage template was borrowed from some colorful folks.