Suchergebnisse - "3D from multi-view and sensors"

NeRFLight: Fast and Light Neural Radiance Fields using a Shared Feature Grid

Autoren: Rivas-Manzaneque, Fernando Sierra Acosta, Jorge Peñate Sánchez, Adrián et al.

Weitere Verfasser: Rivas-Manzaneque, Fernando Sierra Acosta, Jorge Peñate Sánchez, Adrián et al.

Quelle: Digital.CSIC. Repositorio Institucional del CSIC
Consejo Superior de Investigaciones Científicas (CSIC)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [ISSN: 2575-7075], (7-24 June 2023).
accedaCRIS portal de investigación de la Universidad de las Palmas de Gran Canaria
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Conference on Computer Vision and Pattern Recognition (CVPR)

Schlagwörter: Measurement, Metaverse, Data structures, Videojocs, Social networking (online), 16. Peace & justice, Àrees temàtiques de la UPC::Informàtica::Infografia, 7. Clean energy, Three dimensional imaging, Video games, 13. Climate action, Training, 3D from multi-view and sensors, 14. Life underwater, Games, Rendering (computer graphics), 1203 Ciencia de los ordenadores, Imatgeria tridimensional

Dateibeschreibung: application/pdf

Zugangs-URL: https://api.elsevier.com/content/abstract/scopus_id/85173909733
http://hdl.handle.net/10261/351706
http://hdl.handle.net/10553/130228
https://hdl.handle.net/2117/410288
https://doi.org/10.1109/cvpr52729.2023.01195

Open Challenges in Deep Stereo: the Booster Dataset

Autoren: Ramirez, Pierluigi Zama Tosi, Fabio Poggi, Matteo et al.

Quelle: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). :21136-21146

Schlagwörter: FOS: Computer and information sciences, 03 medical and health sciences, 0302 clinical medicine, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, Datasets and evaluation, 3D from multi-view and sensors, 02 engineering and technology

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2206.04671
https://hdl.handle.net/11585/895291
https://doi.org/10.1109/CVPR52688.2022.02049
https://ieeexplore.ieee.org/document/9878667

Decoupling Makes Weakly Supervised Local Feature Better

Autoren: Li, K. (Kunhong) Wang, L. (Longguang) Liu, L. (Li) et al.

Quelle: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). :15817-15827

Schlagwörter: FOS: Computer and information sciences, 03 medical and health sciences, 0302 clinical medicine, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, 3D from multi-view and sensors, Self-& semi-& meta- & unsupervised learning, 02 engineering and technology, Representation learning

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2201.02861
http://urn.fi/urn:nbn:fi-fe2023041135705

RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation

Autoren: Tosi, Fabio Ramirez, Pierluigi Zama Poggi, Matteo et al.

Quelle: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). :15937-15947

Schlagwörter: FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, 3D from multi-view and sensors, Datasets and evaluation, Multispectral imaging, 02 engineering and technology

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2206.07047
https://hdl.handle.net/11585/895292
https://doi.org/10.1109/CVPR52688.2022.01549
https://ieeexplore.ieee.org/document/9879755

3D Shape Modeling with Adaptive Centroidal Voronoi Tesselation on Signed Distance Field

Autoren: Thomas, Diego Franco, Jean-Sébastien Boyer, Edmond

Weitere Verfasser: Thomas, Diego Franco, Jean-Sébastien Boyer, Edmond

Schlagwörter: 3D shape modeling processing and synthesis, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 3D from multi-view and sensors

Dateibeschreibung: application/pdf

Zugangs-URL: https://inria.hal.science/hal-04902175v1

ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks

Autoren: Chuah, WeiQin Tennakoon, Ruwan Hoseinnezhad, Reza et al.

Quelle: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). :13012-13022

Schlagwörter: FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Sciences, Computer Vision and Pattern Recognition (cs.CV), Physical Sciences and Mathematics, Computer Science - Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, 3D from multi-view and sensors, 02 engineering and technology, Machine Learning (cs.LG)

Zugangs-URL: http://arxiv.org/abs/2201.02263

FlowIBR: Leveraging Pre-Training for Efficient Neural Image-Based Rendering of Dynamic Scenes

Autoren: Büsching, Marcel Bengtson, Josef Nilsson, David et al.

Quelle: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024, Seattle, USA IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. :8016-8026

Schlagwörter: Dynamic scenes, 3D from multi-view and sensors, Neural rendering

Zugangs-URL: https://research.chalmers.se/publication/543377

Privacy-Preserving Representations are not Enough: Recovering Scene Content from Camera Poses

Autoren: Chelani, Kunal Sattler, Torsten Kahl, Fredrik et al.

Quelle: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, Canada Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2023-June:13132-13141

Schlagwörter: 3D from multi-view and sensors

Zugangs-URL: https://research.chalmers.se/publication/537969

VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking

Autoren: Chen, Yukang Liu, Jianhui Zhang, Xiangyu et al.

Schlagwörter: 3D from multi-view and sensors

Relation: https://doi.org/10.1109/CVPR52729.2023.02076; http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062531306002

Verfügbarkeit: http://repository.hkust.edu.hk/ir/Record/1783.1-140577
https://doi.org/10.1109/CVPR52729.2023.02076
http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1063-6919&rft.volume=2023-June&rft.issue=&rft.date=2023&rft.spage=21674&rft.aulast=Chen&rft.aufirst=Yukang&rft.atitle=VoxelNeXt%3A+Fully+Sparse+VoxelNet+for+3D+Object+Detection+and+Tracking&rft.title=Proceedings+of+the+IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition
http://www.scopus.com/record/display.url?eid=2-s2.0-85159610423&origin=inward
http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062531306002

Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields

Autoren: Hu, Tao Xu, Xiaogang Liu, Shu et al.

Schlagwörter: 3D from multi-view and sensors

Relation: https://doi.org/10.1109/CVPR52729.2023.00807; http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062522100034

Verfügbarkeit: http://repository.hkust.edu.hk/ir/Record/1783.1-141453
https://doi.org/10.1109/CVPR52729.2023.00807
http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1063-6919&rft.volume=2023-June&rft.issue=&rft.date=2023&rft.spage=8349&rft.aulast=Hu&rft.aufirst=Tao&rft.atitle=Point2Pix%3A+Photo-Realistic+Point+Cloud+Rendering+via+Neural+Radiance+Fields&rft.title=Proceedings+of+the+IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition
http://www.scopus.com/record/display.url?eid=2-s2.0-85170510280&origin=inward
http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062522100034

Spherical Transformer for LiDAR-Based 3D Recognition

Autoren: Lai, Xin Chen, Yukang Lu, Fanbin et al.

Schlagwörter: 3D from multi-view and sensors

Relation: https://doi.org/10.1109/CVPR52729.2023.01683; http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062531301082

Verfügbarkeit: http://repository.hkust.edu.hk/ir/Record/1783.1-141110
https://doi.org/10.1109/CVPR52729.2023.01683
http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1063-6919&rft.volume=2023-June&rft.issue=&rft.date=2023&rft.spage=17545&rft.aulast=Lai&rft.aufirst=Xin&rft.atitle=Spherical+Transformer+for+LiDAR-Based+3D+Recognition&rft.title=Proceedings+of+the+IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition
http://www.scopus.com/record/display.url?eid=2-s2.0-85166198911&origin=inward
http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062531301082

TriVol: Point Cloud Rendering via Triple Volumes

Autoren: Hu, Tao Xu, Xiaogang Chu, Ruihang et al.

Schlagwörter: 3D from multi-view and sensors

Relation: https://doi.org/10.1109/CVPR52729.2023.01986; http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062531305007

Verfügbarkeit: http://repository.hkust.edu.hk/ir/Record/1783.1-141231
https://doi.org/10.1109/CVPR52729.2023.01986
http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1063-6919&rft.volume=2023-June&rft.issue=&rft.date=2023&rft.spage=20732&rft.aulast=Hu&rft.aufirst=Tao&rft.atitle=TriVol%3A+Point+Cloud+Rendering+via+Triple+Volumes&rft.title=Proceedings+of+the+IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition
http://www.scopus.com/record/display.url?eid=2-s2.0-85170494219&origin=inward
http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062531305007

LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs

Autoren: Chen, Yukang Liu, Jianhui Zhang, Xiangyu et al.

Schlagwörter: 3D from multi-view and sensors

Relation: https://doi.org/10.1109/CVPR52729.2023.01296; http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062522105077

Verfügbarkeit: http://repository.hkust.edu.hk/ir/Record/1783.1-140776
https://doi.org/10.1109/CVPR52729.2023.01296
http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1063-6919&rft.volume=2023-June&rft.issue=&rft.date=2023&rft.spage=13488&rft.aulast=Chen&rft.aufirst=Yukang&rft.atitle=LargeKernel3D%3A+Scaling+up+Kernels+in+3D+Sparse+CNNs&rft.title=Proceedings+of+the+IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition
http://www.scopus.com/record/display.url?eid=2-s2.0-85172383384&origin=inward
http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062522105077

3D Video Loops from Asynchronous Input

Autoren: Ma, Li Li, Xiaoyu Liao, Jing et al.

Schlagwörter: 3D from multi-view and sensors

Relation: https://doi.org/10.1109/CVPR52729.2023.00038; http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001058542600030

Verfügbarkeit: http://repository.hkust.edu.hk/ir/Record/1783.1-128514
https://doi.org/10.1109/CVPR52729.2023.00038
http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2023&rft.spage=&rft.aulast=Ma&rft.aufirst=Li&rft.atitle=3D+Video+Loops+from+Asynchronous+Input&rft.title=
http://www.scopus.com/record/display.url?eid=2-s2.0-85173959400&origin=inward
http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001058542600030

CLIP 2 : Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data

Autoren: Zeng, Yihan Jiang, Chenhan Mao, Jiageng et al.

Schlagwörter: 3D from multi-view and sensors

Relation: https://doi.org/10.1109/CVPR52729.2023.01463; http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062522107054

Verfügbarkeit: http://repository.hkust.edu.hk/ir/Record/1783.1-127399
https://doi.org/10.1109/CVPR52729.2023.01463
http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2023&rft.spage=&rft.aulast=Zeng&rft.aufirst=Yihan&rft.atitle=CLIP%5E2%3A+Contrastive+language-image-point+pretraining+from+real-world+point+cloud+data&rft.title=Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition
http://www.scopus.com/record/display.url?eid=2-s2.0-85168643876&origin=inward
http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062522107054

OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation

Autoren: Wu, Tong Zhang, Jiarui Fu, Xiao et al.

Schlagwörter: 3D from multi-view and sensors

Relation: https://doi.org/10.1109/CVPR52729.2023.00084; http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001058542601011

Verfügbarkeit: http://repository.hkust.edu.hk/ir/Record/1783.1-133284
https://doi.org/10.1109/CVPR52729.2023.00084
http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1063-6919&rft.volume=2023-June&rft.issue=&rft.date=2023&rft.spage=803&rft.aulast=Wu&rft.aufirst=Tong&rft.atitle=OmniObject3D%3A+Large-Vocabulary+3D+Object+Dataset+for+Realistic+Perception,+Reconstruction+and+Generation&rft.title=Proceedings+of+the+IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition
http://www.scopus.com/record/display.url?eid=2-s2.0-85173964785&origin=inward
http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001058542601011

Dionysus: Recovering Scene Structures by Dividing into Semantic Pieces

Autoren: Wang, Likang Chen, Lei

Schlagwörter: 3D from multi-view and sensors

Relation: https://doi.org/10.1109/CVPR52729.2023.01210; http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062522104086

Verfügbarkeit: http://repository.hkust.edu.hk/ir/Record/1783.1-132375
https://doi.org/10.1109/CVPR52729.2023.01210
http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1063-6919&rft.volume=2023-June&rft.issue=&rft.date=2023&rft.spage=12576&rft.aulast=Wang&rft.aufirst=Likang&rft.atitle=Dionysus%3A+Recovering+Scene+Structures+by+Dividing+into+Semantic+Pieces&rft.title=Proceedings+of+the+IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition
http://www.scopus.com/record/display.url?eid=2-s2.0-85151846826&origin=inward
http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001062522104086

Revisiting Rotation Averaging : Uncertainties and Robust Losses

Autoren: Zhang, Ganlin Larsson, Viktor Barath, Daniel

Quelle: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 2023-June, pp 17215-17224 (2023) ; ISSN: 1063-6919

Schlagwörter: Computational Mathematics, 3D from multi-view and sensors

Relation: http://dx.doi.org/10.1109/CVPR52729.2023.01651; scopus:85173945874

Verfügbarkeit: https://lup.lub.lu.se/record/cb64a3a3-b4d2-4caa-b1c6-3472dce56bbf
https://doi.org/10.1109/CVPR52729.2023.01651

Four-view Geometry with Unknown Radial Distortion

Autoren: Hruby, Petr Korotynskiy, Viktor Duff, Timothy et al.

Schlagwörter: Computer graphics and computer vision, 3D from multi-view and sensors

Relation: http://dx.doi.org/10.1109/CVPR52729.2023.00868; scopus:85173040982

Verfügbarkeit: https://lup.lub.lu.se/record/ba9e6360-5b8f-40d2-8756-4ebf92eae6ff
https://doi.org/10.1109/CVPR52729.2023.00868

Revisiting the P3P Problem

Autoren: Ding, Yaqing Yang, Jian Larsson, Viktor et al.

Schlagwörter: Computer graphics and computer vision, 3D from multi-view and sensors

Relation: http://dx.doi.org/10.1109/CVPR52729.2023.00472; scopus:85172406023

Verfügbarkeit: https://lup.lub.lu.se/record/5c3f8ae6-a3cf-47c9-90e3-87f20fd8c290
https://doi.org/10.1109/CVPR52729.2023.00472