4,027 Hits in 6.3 sec

Real-time non-rigid reconstruction using an RGB-D camera

Michael Zollhöfer, Christian Theobalt, Marc Stamminger, Matthias Nießner, Shahram Izadi, Christoph Rehmann, Christopher Zach, Matthew Fisher, Chenglei Wu, Andrew Fitzgibbon, Charles Loop
2014 ACM Transactions on Graphics  
Next, a novel GPU pipeline performs non-rigid registration of live RGB-D data to the smooth template using an extended non-linear as-rigid-as-possible (ARAP) framework.  ...  Figure 1 : Our system enables the real-time capture of general shapes undergoing non-rigid deformations using a single depth camera.  ...  It is therefore a natural next step to think about online capture of non-rigid scenes using RGB-D cameras.  ... 
doi:10.1145/2601097.2601165 fatcat:73cjsla3njfwpnuyle4a36lavq

Fast capture of textured full-body avatar with RGB-D cameras

Shuai Lin, Yin Chen, Yu-Kun Lai, Ralph R. Martin, Zhi-Quan Cheng
2016 The Visual Computer  
It uses sixteen RGB-depth (RGB-D) cameras, ten of which are arranged to capture the body, while six target the important head region.  ...  After arranging the cameras, they are calibrated using a mannequin before scanning real humans.  ...  An exception is [14] , which uses a global optimization approach for mapping the color images produced by an RGB-D camera onto the geometric model reconstructed from the corresponding depth data.  ... 
doi:10.1007/s00371-016-1245-9 fatcat:pbwsnorwzvforkw4ufwolebuvq

Non-rigid Reconstruction with a Single Moving RGB-D Camera [article]

Shafeeq Elanattil, Peyman Moghadam, Sridha Sridharan, Clinton Fookes, Mark Cox
2018 arXiv   pre-print
We present a novel non-rigid reconstruction method using a moving RGB-D camera. Current approaches use only non-rigid part of the scene and completely ignore the rigid background.  ...  We are also contributing a synthetic dataset which is made publically available for evaluating non-rigid reconstruction methods.  ...  Figure 1 shows an example of our reconstruction results at different frames. We have developed a synthetic dataset for evaluating RGB-D based non-rigid reconstruction methods.  ... 
arXiv:1805.11219v2 fatcat:7pw7quoa7zbn7f3ouowwlmfczu

Online Reconstruction of Indoor Scenes from RGB-D Streams

Hao Wang, Jun Wang, Liang Wang
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
A system capable of performing robust online volumetric reconstruction of indoor scenes based on input from a handheld RGB-D camera is presented.  ...  Upon termination of scanning, the second pass takes place to handle loop closures and reconstruct the final model using globally refined camera trajectories.  ...  ., about 10 seconds for an indoor sequence that contains two looping points. Recently, [33] uses incremental bundle adjustment with non-rigid deformation for real-time consistent reconstruction.  ... 
doi:10.1109/cvpr.2016.356 dblp:conf/cvpr/WangWW16 fatcat:bpokcmaapff3dkw7cjylkc5gce

SplitFusion: Simultaneous Tracking and Mapping for Non-Rigid Scenes [article]

Yang Li, Tianwei Zhang, Yoshihiko Nakamura, Tatsuya Harada
2020 arXiv   pre-print
We present SplitFusion, a novel dense RGB-D SLAM framework that simultaneously performs tracking and dense reconstruction for both rigid and non-rigid components of the scene.  ...  The split surfaces are independently tracked via rigid or non-rigid ICP and reconstructed through incremental depth map fusion.  ...  Following the fusion technique introduced by [11] [4] , the depth maps segments D t of the real-time RGB-D frame is incrementally integrated into the canonical TSDF.  ... 
arXiv:2007.02108v1 fatcat:evvor74tbbhgdf4e2t3ol2xpzu

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)  
This new version of SLAMBench moves beyond traditional visual SLAM, and provides new support for scene understanding and non-rigid environments (dynamic SLAM).  ...  More concretely for dynamic SLAM, SLAMBench 3.0 includes the first publicly available implementation of DynamicFusion, along with an evaluation infrastructure.  ...  To the best of our knowledge, no implementation of any real-time non-rigid reconstruction system is publicly available.  ... 
doi:10.1109/icra.2019.8794369 dblp:conf/icra/BujancaGSNBODKR19 fatcat:vrvsh7pxxjg4takh2egvjgppxu

DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data [article]

Aljaž Božič, Michael Zollhöfer, Christian Theobalt, Matthias Nießner
2020 arXiv   pre-print
Based on this corpus, we introduce a data-driven non-rigid feature matching approach, which we integrate into an optimization-based reconstruction pipeline.  ...  Our approach significantly outperforms existing non-rigid reconstruction methods that do not use learned data terms, as well as learning-based approaches that only use self-supervision.  ...  Non-Rigid Reconstruction Pipeline We integrate the learned non-rigid matching algorithm into a non-rigid RGB-D reconstruction framework that efficiently tracks dense, space-time coherent, non-rigid deformations  ... 
arXiv:1912.04302v2 fatcat:7t2d3xekyvey3doiszgnjqkwe4

DeepDeform: Learning Non-Rigid RGB-D Reconstruction With Semi-Supervised Data

Aljaz Bozic, Michael Zollhofer, Christian Theobalt, Matthias NieBner
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Based on this corpus, we introduce a data-driven non-rigid feature matching approach, which we integrate into an optimization-based reconstruction pipeline.  ...  Our approach significantly outperforms both existing non-rigid reconstruction methods that do not use learned data terms, as well as learning-based approaches that only use self-supervision.  ...  Non-Rigid Reconstruction Pipeline We integrate the learned non-rigid matching algorithm into a non-rigid RGB-D reconstruction framework that ef-ficiently tracks dense, space-time coherent, non-rigid deformations  ... 
doi:10.1109/cvpr42600.2020.00703 dblp:conf/cvpr/BozicZTN20 fatcat:xugfdxa7wjelvhumz3p4ssuc7u

Better Together: Joint Reasoning for Non-rigid 3D Reconstruction with Specularities and Shading [article]

Qi Liu-Yin, Rui Yu, Lourdes Agapito, Andrew Fitzgibbon, Chris Russell
2017 arXiv   pre-print
We demonstrate the use of shape-from-shading (SfS) to improve both the quality and the robustness of 3D reconstruction of dynamic objects captured by a single camera.  ...  Unlike previous approaches that made use of SfS as a post-processing step, we offer a principled integrated approach that solves dynamic object tracking and reconstruction and SfS as a single unified cost  ...  readily be applied to RGB-D and multi-camera based approaches, and the increased robustness and detailed reconstructions it brings is likely to be of use to the wider community.  ... 
arXiv:1708.01654v1 fatcat:gp2wz3senncmbibikcidiijesu

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

Siim Meerits, Diego Thomas, Vincent Nozick, Hideo Saito
2018 Computational Visual Media  
In this paper, we demonstrate that multiple unsynchronized low-cost RGB-D cameras can be used for the same purpose.  ...  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.  ...  Figure 4 shows an example of interpolation at three different time points using real data.  ... 
doi:10.1007/s41095-018-0121-0 fatcat:uiqymh55ibfmjczikwike5lpma

Deep Textured 3D Reconstruction of Human Bodies [article]

Abbhinav Venkat, Sai Sagar Jinka, Avinash Sharma
2018 arXiv   pre-print
This is achieved by first recovering the volumetric grid of the non-rigid human body given a single view RGB image followed by orthographic texture view synthesis using the respective depth projection  ...  , sparse set of cameras with non-overlapping fields of view, etc.  ...  only at train time) for the task of non-rigid reconstruction.  ... 
arXiv:1809.06547v1 fatcat:cysa6kojvrd6zeqvxcmwf3ntva

Direct, Dense, and Deformable: Template-Based Non-rigid 3D Reconstruction from RGB Video

Rui Yu, Chris Russell, Neill D. F. Campbell, Lourdes Agapito
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
While robust and even real-time solutions exist to this problem if the observed scene is static, for non-rigid dense shape capture current systems are typically restricted to the use of complex multi-camera  ...  We first compute a dense 3D template of the shape of the object, using a short rigid sequence, and subsequently perform online reconstruction of the non-rigid mesh as it evolves over time.  ...  The use of RGB-D sensors has also been extended to markerless capture of non-rigid shapes [14, 15] even in real time [18, 37] .  ... 
doi:10.1109/iccv.2015.111 dblp:conf/iccv/YuRCA15 fatcat:gjutjeyyt5gkhhe3mmcwfuyhk4

VolumeDeform: Real-time Volumetric Non-rigid Reconstruction [article]

Matthias Innmann, Michael Zollhöfer, Matthias Nießner, Christian Theobalt, Marc Stamminger
2016 arXiv   pre-print
We present a novel approach for the reconstruction of dynamic geometric shapes using a single hand-held consumer-grade RGB-D sensor at real-time rates.  ...  The problem is tackled in real-time at the camera's capture rate using a data-parallel flip-flop optimization strategy.  ...  In the past, a variety of methods for dense deformable geometry tracking from multi-view camera systems [9] or a single RGB-D camera, even in real-time [10] , were proposed.  ... 
arXiv:1603.08161v2 fatcat:sksadhn6rrdyhcvq2ve4osx2d4

NRMVS: Non-Rigid Multi-View Stereo [article]

Matthias Innmann, Kihwan Kim, Jinwei Gu, Matthias Niessner, Charles Loop, Marc Stamminger, Jan Kautz
2019 arXiv   pre-print
Scene reconstruction from unorganized RGB images is an important task in many computer vision applications.  ...  We show that creating a dense 4D structure from a few RGB images with non-rigid changes is possible, and demonstrate that our method can be used to interpolate novel deformed scenes from various combinations  ...  More recent RGB-D non-rigid fusion frameworks include KillingFusion [41] and SobolevFusion [42] , which allow for implicit topology changes using advanced regularization techniques.  ... 
arXiv:1901.03910v1 fatcat:tg4vchqqyjhsjlebnk6qwuw2w4

PoseFusion2: Simultaneous Background Reconstruction and Human Shape Recovery in Real-time [article]

Huayan Zhang, Tianwei Zhang, Tin Lun Lam, Sethu Vijayakumar
2021 arXiv   pre-print
In this work, we present a fast, learning-based human object detector to isolate the dynamic human objects and realise a real-time dense background reconstruction framework.  ...  However, humans moving in the scene are often one of the most important, interactive targets - they are very hard to track and reconstruct robustly due to non-rigid shapes.  ...  This sequence was captured in AIRS using an Azure Kinect RGB-D sensor.  ... 
arXiv:2108.00695v1 fatcat:ssobrwmxrjg3tnivh3mhnrjauy
« Previous Showing results 1 — 15 out of 4,027 results