10 Hits in 5.8 sec

BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integration [article]

Angela Dai and Matthias Nießner and Michael Zollhöfer and Shahram Izadi and Christian Theobalt
2017 arXiv   pre-print
model in real-time to ensure global consistency; all within a single framework.  ...  We systematically address these issues with a novel, real-time, end-to-end reconstruction framework.  ...  ACKNOWLEDGMENTS We would like to thank omas Whelan for his help with Elastic-Fusion, and Sungjoon Choi for his advice on the Redwood system.  ... 
arXiv:1604.01093v3 fatcat:meq37nba2jbmdln5dr5y3ooxkq

Efficient Online Surface Correction for Real-time Large-Scale 3D Reconstruction [article]

Robert Maier, Raphael Schaller, Daniel Cremers
2017 arXiv   pre-print
We propose an efficient on-the-fly surface correction method for globally consistent dense 3D reconstruction of large-scale scenes.  ...  State-of-the-art methods for large-scale 3D reconstruction from RGB-D sensors usually reduce drift in camera tracking by globally optimizing the estimated camera poses in real-time without simultaneously  ...  However, only few methods tackle the problem of globally optimizing the camera poses in real-time and simultaneously correcting the reconstructed surface on-the-fly. BundleFusion by Dai et al.  ... 
arXiv:1709.03763v1 fatcat:ado4dzn7ara6fa3acmt22dumm4

FlashFusion: Real-time Globally Consistent Dense 3D Reconstruction using CPU Computing

Lei Han, Lu Fang
2018 Robotics: Science and Systems XIV  
Aiming at the practical usage of dense 3D reconstruction on portable devices, we propose FlashFusion, a Fast LArge-Scale High-resolution (sub-centimeter level) 3D reconstruction system without the use  ...  Extensive experiments on both real world and synthetic datasets demonstrate that FlashFusion succeeds to enable realtime, globally consistent, high-resolution (5mm), and large-scale dense 3D reconstruction  ...  REAL-TIME GLOBALLY CONSISTENT DENSE 3D RECONSTRUCTION USING CPU COMPUTING To elaborate how FlashFusion can enable the global consistency and high efficiency simultenously, this section is organized as  ... 
doi:10.15607/rss.2018.xiv.006 dblp:conf/rss/HanF18 fatcat:j4dfhlwbmveddgylzliqswrtzq

SLAMBench 3.0: Systematic Automated Reproducible Evaluation of SLAM Systems for Robot Vision Challenges and Scene Understanding

Mihai Bujanca, Paul Gafton, Sajad Saeedi, Andy Nisbet, Bruno Bodin, OaBoyle Michael F.P., Andrew J. Davison, Kelly Paul H.J., Graham Riley, Barry Lennox, Mikel Lujan, Steve Furber
2019 2019 International Conference on Robotics and Automation (ICRA)  
Through a series of use-cases, we demonstrate the newly incorporated algorithms, visulation aids and metrics (6 new metrics, 4 new datasets and 5 new algorithms).  ...  In addition, we include two SLAM systems (one dense, one sparse) augmented with convolutional neural networks for scene understanding, together with datasets and appropriate metrics.  ...  Acknowledgments This research is supported by the EPSRC, grant PAMELA EP/K008730/1 and RAIN Hub EP/R026084/1.  ... 
doi:10.1109/icra.2019.8794369 dblp:conf/icra/BujancaGSNBODKR19 fatcat:vrvsh7pxxjg4takh2egvjgppxu

NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video [article]

Jiaming Sun, Yiming Xie, Linghao Chen, Xiaowei Zhou, Hujun Bao
2021 arXiv   pre-print
This design allows the network to capture local smoothness prior and global shape prior of 3D surfaces when sequentially reconstructing the surfaces, resulting in accurate, coherent, and real-time surface  ...  To the best of our knowledge, this is the first learning-based system that is able to reconstruct dense coherent 3D geometry in real-time.  ...  Occupancy Net- globally consistent 3d reconstruction using on-the-fly surface works: Learning 3d reconstruction in function  ... 
arXiv:2104.00681v1 fatcat:gsuhqfhiirbhdeelqolnbwn6hu

FullFusion: A Framework for Semantic Reconstruction of Dynamic Scenes

Mihai Bujanca, Mikel Lujan, Barry Lennox
2019 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)  
We present a framework that enables incremental reconstruction of semantically-annotated 3D models in dynamic settings using commodity RGB-D sensors.  ...  To showcase the potential of FullFusion, we provide a quantitative and qualitative evaluation on a baseline implementation which employs specific reconstruction and segmentation pipelines.  ...  Acknowledgments This research is supported by the EPSRC, grant RAIN Hub EP/R026084/1.  ... 
doi:10.1109/iccvw.2019.00272 dblp:conf/iccvw/BujancaLL19 fatcat:uqnzvmidpjgevgb7kslbjlt46i


M. Weinmann, M. A. Jäger, S. Wursthorn, B. Jutzi, M. Weinmann, P. Hübner
2020 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Abstract. 3D indoor mapping and scene understanding have seen tremendous progress in recent years due to the rapid development of sensor systems, reconstruction techniques and semantic segmentation approaches  ...  However, the quality of the acquired data strongly influences the accuracy of both reconstruction and segmentation.  ...  BundleFusion: real-time globally consistent 3d reconstruction using on-the-fly surface reintegration. ACM Trans. Graph., 36(3), 24:1-24:18. Demantké, J., Mallet, C., David, N., Vallet, B., 2011.  ... 
doi:10.5194/isprs-annals-v-1-2020-165-2020 fatcat:43tw2hriu5gshckub6wftcdlxy

LIME: Live Intrinsic Material Estimation [article]

Abhimitra Meka, Maxim Maximov, Michael Zollhoefer, Avishek Chatterjee, Hans-Peter Seidel, Christian Richardt, Christian Theobalt
2018 arXiv   pre-print
The estimation of material parameters at real time frame rates enables exciting mixed reality applications, such as seamless illumination consistent integration of virtual objects into real world scenes  ...  We tackle this challenging and ill posed inverse rendering problem using recent advances in image to image translation techniques based on deep convolutional encoder decoder architectures.  ...  the Symposium on User Interface Software and Technology BundleFusion: Real-time globally consistent 3D reconstruc- (UIST), pages 559–568, 2011.  ... 
arXiv:1801.01075v2 fatcat:bxvrwkxkgnhq5owufhqwzgrfre

Multi-Robot Active Mapping via Neural Bipartite Graph Matching [article]

Kai Ye, Siyan Dong, Qingnan Fan, He Wang, Li Yi, Fei Xia, Jue Wang, Baoquan Chen
2022 arXiv   pre-print
We study the problem of multi-robot active mapping, which aims for complete scene map construction in minimum time steps.  ...  Previous approaches either choose the frontier as the goal position via a myopic solution that hinders the time efficiency, or maximize the long-term value via reinforcement learning to directly regress  ...  We thank the anonymous reviewers for their valuable comments. This work was supported by NSFC (62161146002).  ... 
arXiv:2203.16319v2 fatcat:rzwwqe72qndf7nmxc2p4slzl3a

Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope [article]

Tolga Birdal, Umut Şimşekli
2019 arXiv   pre-print
We show on both synthetic and real datasets that we achieve high quality multi-graph matching results with faster convergence and reliable confidence/uncertainty estimates.  ...  Langevin Monte Carlo for generating samples on the Birkhoff Polytope and estimating the confidence of the found solutions.  ...  Acknowledgements Supported by the grant ANR-16-CE23-0014 (FBIMATRIX). Authors thank Haowen Deng for the initial 3D correspondences and, Benjamin Busam and Jesus Briales for fruitful discussions.  ... 
arXiv:1904.05814v1 fatcat:ngqtrdaakzfujbqm3scvkptajq