{"type":"ScholarlyArticle","title":"Active Object Reconstruction Using a Guided View Planner","authors":[{"name":"Xin Yang","slug":"xin-yang","given":"Xin","family":"Yang","affiliation":"Dalian University of Technology; City University of Hong Kong"},{"name":"Yuanbo Wang","slug":"yuanbo-wang","given":"Yuanbo","family":"Wang","affiliation":"Dalian University of Technology"},{"name":"Yaru Wang","slug":"yaru-wang","given":"Yaru","family":"Wang","affiliation":"Dalian University of Technology"},{"name":"Baocai Yin","slug":"baocai-yin","given":"Baocai","family":"Yin","affiliation":"Dalian University of Technology"},{"name":"Qiang Zhang","slug":"qiang-zhang","given":"Qiang","family":"Zhang","affiliation":"Dalian University of Technology"},{"name":"Xiaopeng Wei","slug":"xiaopeng-wei","given":"Xiaopeng","family":"Wei","affiliation":"Dalian University of Technology"},{"name":"Hongbo Fu","slug":"hongbo-fu","given":"Hongbo","family":"Fu","affiliation":"City University of Hong Kong"}],"abstract":"Inspired by the recent advance of image-based object reconstruction using deep learning, we present an active reconstruction model using a guided view planner. We aim to reconstruct a 3D model using images observed from a planned sequence of informative and discriminative views. But where are such informative and discriminative views around an object? To address this we propose a unified model for view planning and object reconstruction, which is utilized to learn a guided information acquisition model and to aggregate information from a sequence of images for reconstruction. Experiments show that our model (1) increases our reconstruction accuracy with an increasing number of views (2) and generally predicts a more informative sequence of views for object reconstruction compared to other alternative methods.","doi":"10.24963/ijcai.2018/689","url":"https://ijcai.org/proceedings/2018/689","pdf":"https://ijcai.org/proceedings/2018/0689.pdf","markdown":"https://ijcai.org/proceedings/2018/689.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/689","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Robotics","track":"Main track","number":689,"pages":{"first":4965,"last":4971},"keywords":["Robotics: Robotics and Vision","Computer Vision: Structural and Model-Based Approaches, Knowledge Representation and Reasoning","Computer Vision: 2D and 3D Computer Vision"],"videos":[],"references":[{"position":1,"raw":"[Choy et al., 2016] Christopher B Choy, Danfei Xu, JunY- oung Gwak, Kevin Chen, and Silvio Savarese. 3d-r2n2: A unified approach for single and multi-view 3d object re- construction. In European Conference on Computer Vi- sion, 2016.","title":"3d-r2n2: A unified approach for single and multi-view 3d object reconstruction","authors":"Danfei Christopher B Choy, Junyoung Xu, Kevin Gwak, Silvio Chen, Savarese","year":"2016","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Dai et al., 2017] Angela Dai, Charles Ruizhongtai Qi, and Matthias Nießner. Shape completion using 3d-encoder- predictor cnns and shape synthesis. In Computer Vision and Pattern Regognition, 2017.","title":"Shape completion using 3d-encoderpredictor cnns and shape synthesis","authors":"Angela Dai, Charles Ruizhongtai Qi, Matthias Nießner","year":"2017","venue":"Computer Vision and Pattern Regognition","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Denzler and Brown, 2002] J Denzler and C Brown. An in- formation theoretic approach to optimal sensor data selec- tion for state estimation. Pattern Analysis and Machine Intelligence, 2002.","title":"An information theoretic approach to optimal sensor data selection for state estimation","authors":"Brown ; ] J Denzler, C Denzler, Brown","year":"2002","venue":"Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fan et al., 2017] Haoqiang Fan, Hao Su, and Leonidas Guibas. A point set generation network for 3d object re- construction from a single image. In Computer Vision and Pattern Regognition, 2017.","title":"A point set generation network for 3d object reconstruction from a single image","authors":"Fan","year":"2017","venue":"Computer Vision and Pattern Regognition","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Girdhar et al., 2016] Rohit Girdhar, David F Fouhey, Mikel Rodriguez, and Abhinav Gupta. Learning a predictable and generative vector representation for objects. In Euro- pean Conference on Computer Vision, 2016.","title":"Learning a predictable and generative vector representation for objects","authors":"Rohit Girdhar, David F Fouhey, Mikel Rodriguez, Abhinav Gupta","year":"2016","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Halber and Funkhouser, 2017] Maciej Halber and Thomas Funkhouser. Fine-to-coarse global registration of rgb-d scans. In Computer Vision and Pattern Recognition, 2017.","title":"Fine-to-coarse global registration of rgb-d scans","authors":"Funkhouser Halber, Maciej Halber, Thomas Funkhouser","year":"2017","venue":"Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Huber et al., 2012] Marco F Huber, Tobias Dencker, Ma- soud Roschani, and Jürgen Beyerer. Bayesian active ob- ject recognition via gaussian process regression. In Infor- mation Fusion, 2012.","title":"Bayesian active object recognition via gaussian process regression","authors":"Tobias Marco F Huber, Masoud Dencker, Jürgen Roschani, Beyerer","year":"2012","venue":"Information Fusion","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kar et al., 2015] Abhishek Kar, Shubham Tulsiani, Joao Carreira, and Jitendra Malik. Category-specific object re- construction from a single image. In Computer Vision and Pattern Recognition, 2015.","title":"Category-specific object reconstruction from a single image","authors":"Abhishek Kar, Shubham Tulsiani, Joao Carreira, Jitendra Malik","year":"2015","venue":"Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Mnih et al., 2014] Volodymyr Mnih, Nicolas Heess, Alex Graves, et al. Recurrent models of visual attention. In Ad- vances in Neural Information Processing Systems, 2014.","title":"Recurrent models of visual attention","authors":"Volodymyr Mnih, Nicolas Heess, Alex Graves","year":"2014","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Snavely et al., 2006] Noah Snavely, Steven M Seitz, and Richard Szeliski. Photo tourism: Exploring photo collec- tions in 3d. ACM Transactions on Graphics, 2006.","title":"Photo tourism: Exploring photo collections in 3d","authors":"Snavely","year":"2006","venue":"ACM Transactions on Graphics","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Tatarchenko et al., 2017] Maxim Tatarchenko, Alexey Dosovitskiy, and Thomas Brox. Octree generating networks: Efficient convolutional architectures for high- resolution 3d outputs. In International Conference on Computer Vision, 2017.","title":"Maxim Tatarchenko, Alexey Dosovitskiy, and Thomas Brox. Octree generating networks: Efficient convolutional architectures for highresolution 3d outputs","authors":"Tatarchenko","year":"2017","venue":"International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Wu et al., 2014] Shihao Wu, Wei Sun, Pinxin Long, Hui Huang, Daniel Cohen-Or, Minglun Gong, Oliver Deussen, and Baoquan Chen. Quality-driven poisson-guided au- toscanning. ACM Transactions on Graphics, 2014.","title":"Quality-driven poisson-guided autoscanning","authors":"Shihao Wu, Wei Sun, Pinxin Long, Hui Huang, Daniel Cohen-Or, Minglun Gong, Oliver Deussen, Baoquan Chen","year":"2014","venue":"ACM Transactions on Graphics","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Wu et al., 2015] Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 3d shapenets: A deep representation for volumet- ric shapes. In Computer Vision and Pattern Recognition, 2015.","title":"3d shapenets: A deep representation for volumetric shapes","authors":"Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, Jianxiong Xiao","year":"2015","venue":"Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Wu et al., 2016a] Jiajun Wu, Tianfan Xue, Joseph J Lim, Yuandong Tian, Joshua B Tenenbaum, Antonio Torralba, and William T Freeman. Single image 3d interpreter net- work. In European Conference on Computer Vision, 2016.","title":"Single image 3d interpreter network","authors":"Wu","year":"2016","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Wu et al., 2016b] Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman, and Josh Tenenbaum. Learning a prob- abilistic latent space of object shapes via 3d generative- adversarial modeling. In Advances in Neural Information Processing Systems, 2016.","title":"Learning a probabilistic latent space of object shapes via 3d generativeadversarial modeling","authors":"Wu","year":"2016","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Xiao et al., 2015] Tianjun Xiao, Yichong Xu, Kuiyuan Yang, Jiaxing Zhang, Yuxin Peng, and Zheng Zhang. The application of two-level attention models in deep convolu- tional neural network for fine-grained image classification. In Computer Vision and Pattern Recognition, 2015.","title":"The application of two-level attention models in deep convolutional neural network for fine-grained image classification","authors":"Xiao","year":"2015","venue":"Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Xu et al., 2015] Kai Xu, Hui Huang, Yifei Shi, Hao Li, Pinxin Long, Jianong Caichen, Wei Sun, and Baoquan Chen. Autoscanning for coupled scene reconstruction and proactive object analysis. ACM Transactions on Graphics, 2015.","title":"Autoscanning for coupled scene reconstruction and proactive object analysis","authors":"Kai Xu, Hui Huang, Yifei Shi, Hao Li, Pinxin Long, Jianong Caichen, Wei Sun, Baoquan Chen","year":"2015","venue":"ACM Transactions on Graphics","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Xu et al., 2016] Kai Xu, Yifei Shi, Lintao Zheng, Junyu Zhang, Min Liu, Hui Huang, Hao Su, Daniel Cohen-Or, and Baoquan Chen. 3d attention-driven depth acquisition for object identification. ACM Transactions on Graphics, 2016.","title":"3d attention-driven depth acquisition for object identification","authors":"Kai Xu, Yifei Shi, Lintao Zheng, Junyu Zhang, Min Liu, Hui Huang, Hao Su, Daniel Cohen-Or, Baoquan Chen","year":"2016","venue":"ACM Transactions on Graphics","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Yan et al., 2016] Xinchen Yan, Jimei Yang, Ersin Yumer, Yijie Guo, and Honglak Lee. Perspective transformer nets: Learning single-view 3d object reconstruction without 3d supervision. In Advances in Neural Information Process- ing Systems, 2016.","title":"Perspective transformer nets: Learning single-view 3d object reconstruction without 3d supervision","authors":"Yan","year":"2016","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}