Filters








59,782 Hits in 9.2 sec

A framework for ultra high resolution 3D imaging

Zheng Lu, Yu-Wing Tai, Moshe Ben-Ezra, Michael S. Brown
2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Based on this multi-resolution reconstruction scheme, our imaging framework can produce 3D scans that show exceptionally detailed 3D surfaces far exceeding existing technologies.  ...  To deal with these resolution differences, we propose a multi-resolution surface reconstruction scheme that propagates the low-resolution geometric constraints through the different frequency bands while  ...  G04090064) and NUS RFC (No. R-252-000-423-112). We gratefully acknowledge Judy Brown, Yasuyuki Matsushita, Yi Ma, and the anonymous reviewers for their useful suggestions towards improving this paper.  ... 
doi:10.1109/cvpr.2010.5539829 dblp:conf/cvpr/LuTBB10 fatcat:sqbf2x27tnau3gxcxyfu2kavfi

Spatially Continuous and High-resolution Land Surface Temperature: A Review of Reconstruction and Spatiotemporal Fusion Techniques [article]

Penghai Wu, Zhixiang Yin, Chao Zeng, Sibo Duan, Frank-Michael Gottsche, Xiaoshaung Ma, Xinghua Li, Hui Yang, Huanfeng Shen
2019 arXiv   pre-print
(PMW)-based and Surface Energy Balance (SEB)-based methods) and three kinds of spatiotemporal fusion methods (weighted function-based, unmixing-based and hybrid methods).  ...  Remotely sensed, spatially continuous and high spatiotemporal resolution (hereafter referred to as high resolution) land surface temperature (LST) is a key parameter for studying the thermal environment  ...  Among the recently developed methods are reconstruction and spatiotemporal fusion based on the deep learning framework.  ... 
arXiv:1909.09316v1 fatcat:vuh27iundzcofko7httat6kocm

Monocular, Real-Time Surface Reconstruction Using Dynamic Level of Detail

Jacek Zienkiewicz, Akis Tsiotsios, Andrew Davison, Stefan Leutenegger
2016 2016 Fourth International Conference on 3D Vision (3DV)  
While most of the existing reconstruction approaches rely on volumetric or point-cloud representations of the environment, we perform depth-map and colour fusion directly into a multi-resolution triangular  ...  Our method relies on least-squares optimisation, which enables a probabilistically sound and principled formulation of the fusion algorithm.  ...  Multi-scale fusion Our multi-scale fusion approach combines Laplacian-based surface decomposition, dynamic tessellation and level of detail, and optimisation-based surface reconstruction within a single  ... 
doi:10.1109/3dv.2016.82 dblp:conf/3dim/ZienkiewiczTDL16 fatcat:pjwkrkpzbjesblvsgmdatv2hb4

SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization [article]

Yue Jiang, Dantong Ji, Zhizhong Han, Matthias Zwicker
2022 arXiv   pre-print
We apply our approach to the problem of multi-view 3D reconstruction, where we achieve high reconstruction quality and can capture complex topology of 3D objects.  ...  In particular, we apply our method to single-view 3D reconstruction and achieve state-of-the-art results.  ...  Therefore, we apply a coarse-to-fine multi-resolution approach. We start by initializing the SDF grid at a resolution of 8 3 to the SDF of a sphere.  ... 
arXiv:1912.07109v2 fatcat:7gjbfiqpnfeb3bt2btskwu6p6a

Complete multi-view reconstruction of dynamic scenes from probabilistic fusion of narrow and wide baseline stereo

Tony Tung, Shohei Nobuhara, Takashi Matsuyama
2009 2009 IEEE 12th International Conference on Computer Vision  
In particular we present an original probabilistic framework to derive and predict the true surface of models.  ...  This paper presents a novel approach to achieve accurate and complete multi-view reconstruction of dynamic scenes (or 3D videos). 3D videos consist in sequences of 3D models in motion captured by a surrounding  ...  Acknowledgments This work was supported in part by the Japan Society for the Promotion of Science (JSPS No.20.08366), MEXT of Japan under the GCOE program "Informatics Education and Research Center for  ... 
doi:10.1109/iccv.2009.5459384 dblp:conf/iccv/TungNM09 fatcat:s5543fddybbopm72pvqo6ruqrm

Consistent cortical reconstruction and multi-atlas brain segmentation

Yuankai Huo, Andrew J. Plassard, Aaron Carass, Susan M. Resnick, Dzung L. Pham, Jerry L. Prince, Bennett A. Landman
2016 NeuroImage  
multi-atlas segmentation with the cortical reconstruction method CRUISE.  ...  In this work, we propose a novel "multi-atlas segmentation to surface" method called Multi-atlas CRUISE (MaCRUISE), which achieves self-consistent whole brain segmentations and cortical surfaces by combining  ...  This study was also supported by NIH 5R01NS056307, 5R21NS082891 and in part using the resources of the Advanced Computing Center for Research and Education  ... 
doi:10.1016/j.neuroimage.2016.05.030 pmid:27184203 pmcid:PMC4927397 fatcat:aagizrwmujaktlmfkp7atpou2i

Multi-level differential surface representation based on local transformations

Dong Xu, Wei Chen, Hongxin Zhang, Hujun Bao
2006 The Visual Computer  
One crucial issue of multi-resolution surface representations is how to effectively record and reconstruct geometric details among surface levels.  ...  In this paper we propose an alternative detail representation and reconstruction scheme, based on local transformations on a per-triangle basis.  ...  In a multi-resolution framework, the detail information between consecutive levels has to be extracted in advance and reconstructed after modifications of the base level.  ... 
doi:10.1007/s00371-006-0024-4 fatcat:3nwnnhwb7vdkvjpi5yltx22mee

Better Together: Shading Cues and Multi-View Stereo for Reconstruction Depth Optimization

Zhe Liang, Chao Xu, Jing Hu, Yushi Li, Zhaopeng Meng
2020 IEEE Access  
In this paper, we make use of geometric and shading cues information in the multi-view stereo approach to construct a robust energy function, which is also effective to optimize the depth information provided  ...  Passive reconstruction methods such as traditional multi-view stereo are capable to accurate reconstruction results.  ...  ACKNOWLEDGMENT The authors are grateful to the monographs of these scholars. Without the inspiration and help of these scholars, they will not be able to complete the final writing of this paper.  ... 
doi:10.1109/access.2020.3003023 fatcat:wlumm47tafb6hcl6pp3sjnxjxq

Sparsity Based Full Rank Polarimetric Reconstruction of Coherence Matrix T

Hossein Aghababaee, Giampaolo Ferraioli, Laurent Ferro-Famil, Gilda Schirinzi, Yue Huang
2019 Remote Sensing  
Under the frame of compressive sensing (CS) and sparsity based reconstruction, the profile of second order polarimetric coherence matrix T is recovered.  ...  The objective of this study is to evaluate the performance of the proposed full-rank polarimetric reconstruction by means of conventional three-component decomposition of T, and focusing on the consistency  ...  Acknowledgments: The authors would like to thank the ESA Earth Observation Campaigns Data Project for providing MB TropiSAR data. Conflicts of Interest: The authors declare no conflicts of interest.  ... 
doi:10.3390/rs11111288 fatcat:uaiohk3irzhllk6johbby2lf2y

Scaled-neighborhood Patches Fusion for Multi-view Stereopsis

Ning An, Yicong He, Hang Dong, Fei Wang, K. Abou-El-Hossein
2016 MATEC Web of Conferences  
In this paper, we present a multi-view stereo reconstruction approach which fuses scaled-neighborhood information.  ...  And it has been tested that employing the scaled-window will dramatically smooth the surfaces and enhance the reconstruction precision.  ...  Acknowledgment This work was supported by the Natural Science Foundation of China (No61273366), National High Technology Research and Development Program (No2015BAH31F01).  ... 
doi:10.1051/matecconf/20165408006 fatcat:gsb6qg7jjjcgxozkpopthxcjia

Multi-Resolution 3D Mapping with Explicit Free Space Representation for Fast and Accurate Mobile Robot Motion Planning [article]

Nils Funk, Juan Tarrio, Sotiris Papatheodorou, Marija Popovic, Pablo F. Alcantarilla, Stefan Leutenegger
2021 arXiv   pre-print
We introduce a method for choosing resolution -- on the fly -- in real-time by means of a multi-scale max-min pooling of the input depth image.  ...  With the aim of bridging the gap between high quality reconstruction and mobile robot motion planning, we propose an efficient system that leverages the concept of adaptive-resolution volumetric mapping  ...  Contrary to methods based on signed distance functions, we continuously maintain a high resolution 3D octree representation of observed occupied and free space in real-time.  ... 
arXiv:2010.07929v5 fatcat:as2eaqmg6zgg7j46zxmklzm2v4

A 3D Imaging Framework Based on High-Resolution Photometric-Stereo and Low-Resolution Depth

Zheng Lu, Yu-Wing Tai, Fanbo Deng, Moshe Ben-Ezra, Michael S. Brown
2012 International Journal of Computer Vision  
The first is a multi-resolution, patched-based surface reconstruction scheme that can robustly handle the significant resolution difference between our surface normals and depth samples.  ...  This paper introduces a 3D imaging framework that combines high-resolution photometric stereo and lowresolution depth.  ...  Fig. 10 Example of the benefits of the multi-resolution scheme: a our surface reconstruction directly using the low-resolution geometry, b reconstructed surface using the multi-resolution scheme.  ... 
doi:10.1007/s11263-012-0589-5 fatcat:yqt5vfciwbh6nnrkwqzf5vh6pa

Mesh-based Multi-view Normal Integration with Energy Minimization Using Surface Reflectance Properties

Wichayut Eaksarayut, Pitchaya Sitthi-amorn, Borom Tunwattanapong, Nuttapong Chentanez
2018 Journal of WSCG  
Our core optimization framework uses multi-view normal integration, which can recovers water-tight surface of the object iteratively in a coarse to fine manner.  ...  We also employ the idea of multi-resolution and weighted data heuristic which helps dealing with noisy data and improves both accuracy and optimization time.  ...  an error functional minimization framework based on the conventional shapefrom-shading approach [13] .  ... 
doi:10.24132/jwscg.2018.26.2.3 fatcat:gy4vpyjc4bgsfmvpk42imi4tcq

Shading-based dynamic shape refinement from multi-view video under general illumination

Chenglei Wu, Kiran Varanasi, Yebin Liu, Hans-Peter Seidel, Christian Theobalt
2011 2011 International Conference on Computer Vision  
Our method starts off from a set of multi-view video frames and an initial series of reconstructed coarse 3D meshes that lack any surface detail.  ...  In a spatio-temporal maximum a posteriori probability (MAP) inference framework, our approach first estimates the incident illumination and the spatiallyvarying albedo map on the mesh surface for every  ...  Various methods for static 3D surface reconstruction have been proposed that are based on these advances. Basri et al.  ... 
doi:10.1109/iccv.2011.6126358 dblp:conf/iccv/WuVLST11 fatcat:kkcwh7jr7jecjggkpkm3dzujlu

High Resolution Surface Reconstruction from Multi-view Aerial Imagery

Fatih Calakli, Ali O. Ulusoy, Maria I. Restrepo, Gabriel Taubin, Joseph L. Mundy
2012 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission  
This paper presents a novel framework for surface reconstruction from multi-view aerial imagery of large scale urban scenes, which combines probabilistic volumetric modeling with smooth signed distance  ...  , the algorithm learns the geometry and appearance of a scene from a calibrated image sequence.  ...  ACKNOWLEDGEMENT This material describes work supported by the National Science Foundation under Grants No. IIS-0808718, and CCF-0915661.  ... 
doi:10.1109/3dimpvt.2012.54 dblp:conf/3dim/CalakliURTM12 fatcat:cdtv4et65jf4bettmnna63vke4
« Previous Showing results 1 — 15 out of 59,782 results