FusionMLS: Highly dynamic 3D reconstruction with consumer-grade RGB-D cameras

Siim Meerits (1) , Diego Thomas (2) , Vincent Nozick (3, 4) , Hideo Saito (1)

1 hvrl - hyper vision research lab
2 Kyushu University
3 LIGM - Laboratoire d'Informatique Gaspard-Monge
4 JFLI - Japanese French Laboratory for Informatics

Multi-view dynamic three-dimensional reconstruction has typically required the use of custom shutter-synchronized camera rigs in order to capture scenes containing rapid movements or complex topology changes. In this paper, we demonstrate that multiple unsynchronized low-cost RGB-D cameras can be used for the same purpose. To alleviate issues caused by unsynchronized shutters, we propose a novel depth frame interpolation technique that allows synchronized data capture from highly dynamic 3D scenes. To manage the resulting huge number of input depth images, we also introduce an efficient moving least squares-based volumetric reconstruction method that generates triangle meshes of the scene. Our approach does not store the reconstruction volume in memory, making it memory-efficient and scalable to large scenes. Our implementation is completely GPU based and works in real time. The results shown herein, obtained with real data, demonstrate the effectiveness of our proposed method and its advantages compared to state-of-the-art approaches.

Mots clés: 3D reconstruction; RGB-D cameras; motion capture; GPU

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]

Siim Meerits, Diego Thomas, Vincent Nozick, Hideo Saito. FusionMLS: Highly dynamic 3D reconstruction with consumer-grade RGB-D cameras. Computational Visual Media, 2018, ⟨10.1007/s41095-018-0121-0⟩. ⟨hal-01912786⟩