دورية أكاديمية
FusionMLS: Highly dynamic 3D reconstruction with consumer-grade RGB-D cameras
العنوان: | FusionMLS: Highly dynamic 3D reconstruction with consumer-grade RGB-D cameras |
---|---|
المؤلفون: | Meerits, Siim, Thomas, Diego, Nozick, Vincent, Saito, Hideo |
المساهمون: | hyper vision research lab (hvrl), Kyushu University, Laboratoire d'Informatique Gaspard-Monge (LIGM), Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout (BEZOUT), Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Japanese French Laboratory for Informatics (JFLI), National Institute of Informatics (NII)-Université Pierre et Marie Curie - Paris 6 (UPMC)-The University of Tokyo (UTokyo)-Centre National de la Recherche Scientifique (CNRS) |
المصدر: | ISSN: 2096-0433 ; Computational Visual Media ; https://hal.science/hal-01912786Test ; Computational Visual Media, 2018, ⟨10.1007/s41095-018-0121-0⟩. |
بيانات النشر: | HAL CCSD Springer |
سنة النشر: | 2018 |
مصطلحات موضوعية: | 3D reconstruction, RGB-D cameras, motion capture, GPU, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] |
الوصف: | International audience ; 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. |
نوع الوثيقة: | article in journal/newspaper |
اللغة: | English |
العلاقة: | hal-01912786; https://hal.science/hal-01912786Test; https://hal.science/hal-01912786/documentTest; https://hal.science/hal-01912786/file/CVM0121_proof.pdfTest |
DOI: | 10.1007/s41095-018-0121-0 |
الإتاحة: | https://doi.org/10.1007/s41095-018-0121-0Test https://hal.science/hal-01912786Test https://hal.science/hal-01912786/documentTest https://hal.science/hal-01912786/file/CVM0121_proof.pdfTest |
حقوق: | info:eu-repo/semantics/OpenAccess |
رقم الانضمام: | edsbas.23017B35 |
قاعدة البيانات: | BASE |
DOI: | 10.1007/s41095-018-0121-0 |
---|