RECONSTRUCTING PART-LEVEL 3D MODELS FROM A SINGLE IMAGE

被引:1
作者
Shi, Dingfeng [1 ]
Zhao, Yifan [1 ]
Li, Jia [1 ,2 ]
机构
[1] Beihang Univ, SCSE, State Key Lab Virtual Real Technol & Syst, Beijing, Peoples R China
[2] Beihang Univ, Beijing Adv Innovat Ctr Big Data & Brain Comp, Beijing, Peoples R China
来源
2020 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME) | 2020年
基金
中国国家自然科学基金;
关键词
3D reconstruction; single-view; part-level;
D O I
10.1109/icme46284.2020.9102773
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Understanding an image with 3D representations has been an increasingly attractive topic in computer vision. The state-of-the-art 3D reconstruction methods usually focus on the reconstruction of the holistic object, while missing important part information, which is crucial in robotic interaction and virtual reality applications. To solve this issue, we make the first attempt to reconstruct the 3D models with part-level representations in a unified framework. With the input of the singleview images, we first develop a feature enhancement encoder to incorporate discriminative local features into the feature representation. The local features are selected adaptively by a learnable local awareness module. Then the enhanced local features are fused with the global branch to form the 3D representations. We then develop a 3D part generator to decode the image priors to 3D parts with a 3D focal loss, which enables the representations of small parts. Experimental results indicate that our model generates reliable part-level structures while achieving state-of-the-art performance in object-level recovering.
引用
收藏
页数:6
相关论文
共 50 条
[21]   SingleRecon: Reconstructing Building 3-D Models of LoD1 From a Single Off-Nadir Remote Sensing Image [J].
Shao, Ruizhe ;
Wu, Jiangjiang ;
Li, Jun ;
Peng, Shuang ;
Chen, Hao ;
Du, Chun .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 :19588-19600
[22]   Reconstructing a 3D structure from serial histological sections [J].
Ourselin, S ;
Roche, A ;
Subsol, G ;
Pennec, X ;
Ayache, N .
IMAGE AND VISION COMPUTING, 2001, 19 (1-2) :25-31
[23]   Reconstructing 3D compact sets [J].
Cazals, Frederic ;
Cohen-Steiner, David .
COMPUTATIONAL GEOMETRY-THEORY AND APPLICATIONS, 2012, 45 (1-2) :1-13
[24]   Window projection with Bayesian diffusion for 3D shape reconstruction from single low-light-level image [J].
Wang, Feng ;
Yin, Liju ;
Qin, Yiming ;
Gao, Xiaoning ;
Tang, Xiangyu ;
Zhou, Hui .
DIGITAL SIGNAL PROCESSING, 2025, 162
[25]   Reconstructing 3D Face Models by Incremental Aggregation and Refinement of Depth Frames [J].
Pala, Pietro ;
Berretti, Stefano .
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2019, 15 (01)
[26]   3D point cloud generation reconstruction from single image based on image retrieval☆ [J].
Chen, Hui ;
Zuo, Yipeng ;
Tong, Yong ;
Zhu, Li .
RESULTS IN OPTICS, 2021, 5
[27]   A Weighted Color MRF Model for 3D Reconstruction from a Single Image [J].
Pan, Yunpeng ;
Zhou, Mingquan ;
Fan, Yachun ;
Zhang, Dongdong ;
Zheng, Xia .
2013 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY AND VISUALIZATION (ICVRV 2013), 2013, :21-27
[28]   A Geometry-Based 3D Reconstruction from a Single Omnidirectional Image [J].
Wahyono ;
Joko, Hariyono ;
Vavilin, Andrey ;
Jo, Kang-Hyun .
PROCEEDINGS OF THE 19TH KOREA-JAPAN JOINT WORKSHOP ON FRONTIERS OF COMPUTER VISION (FCV 2013), 2013, :295-299
[29]   Application of Deep Learning to 3D Object Reconstruction From a Single Image [J].
Chen J. ;
Zhang Y.-Q. ;
Song P. ;
Wei Y.-T. ;
Wang Y. .
Zidonghua Xuebao/Acta Automatica Sinica, 2019, 45 (04) :657-668
[30]   Attention-based 3D Object Reconstruction from a Single Image [J].
Salvi, Andrey ;
Gavenski, Nathan ;
Pooch, Eduardo ;
Tasoniero, Felipe ;
Barros, Rodrigo .
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,