Robotics and Computer Vision Lab

Publications

조회 수 790 댓글 0
Extra Form
저 자 Seong-Heum Kim, Yu-Wing Tai, Joon-Young Lee, Jaesik Park, In So Kweon
학 회 Computer Graphics Forum (invited to Eurographics 2017)
Notes This work was supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIP) and Korea Creative Content Agency(KOCCA) grant funded by the Korea government(MCST) (R0132-15-1006, Developing the technology of open composable content editors for realistic media).
논문일시(Year) 2017
논문일시(Month) 04
In this paper, we present a new framework to determine up front orientations and detect salient views of 3D models. The salient viewpoint to human preferences is the most informative projection with correct upright orientation. Our method utilizes two Convolutional Neural Network (CNN) architectures to encode category-specific information learnt from a large number of 3D shapes and 2D images on the web. Using the first CNN model with 3D voxel data, we generate a CNN shape feature to decide natural upright orientation of 3D objects. Once a 3D model is upright-aligned, the front projection and salient views are scored by category recognition using the second CNN model. The second CNN is trained over popular photo collections from internet users. In order to model comfortable viewing angles of 3D models, a category dependent prior is also learnt from the users. Our approach effectively combines category-specific scores and classical evaluations to produce a data-driven viewpoint saliency map. The best viewpoints from the method are quantitatively and qualitatively validated with more than 100 objects from 20 categories. Our thumbnail images of 3D models are the most favored among those from different approaches.

List of Articles
» Category-specific Salient View Selection via Deep Convolutional Neural Networks
Seong-Heum Kim, Yu-Wing Tai, Joon-Young Lee, Jaesik Park, In So Kweon
Computer Graphics Forum (invited to Eurographics 2017) 2017 / 04
503. Robust Multiview Photometric Stereo using Planar Mesh Parameterization
Jaesik Park, Sudipta N. Sinha, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2016 / 08
502. Automatic Trimap Generation and Consistent Matting for Light-Field Images
Donghyeon Cho, Sunyeong Kim, Yu-Wing Tai, In So Kweon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016 2016 / 08
501. A Real-time Vehicular Vision System to Seamlessly See-through Cars
Francois Rameau, Hyowon Ha, Kyungdon Joo, Jinsoo Choi, In So Kweon
European Conference on Computer Vision Workshops (ECCVW - ACVR) 2016 / 10
500. A Real-time Augmented Reality System to See-Through Cars
Francois Rameau, Hyowon Ha, Kyungdon Joo, Jinsoo Choi, Kibaek Park, In So Kweon
IEEE Transactions on Visualization and Computer Graphics (TVCG) 2016 / 09
499. A Real-time Augmented Reality System to See-Through Cars
Francois Rameau, Hyowon Ha, Kyungdon Joo, Jinsoo Choi, Kibaek Park, In So Kweon
IEEE International Symposium on Mixed and Augmented Reality (ISMAR) 2016 / 09
498. Pixel-Level Domain Transfer
Donggeun Yoo, Namil Kim, Sunggyun Park, Anthony S. Paek, In So Kweon
European Conference on Computer Vision (ECCV) 2016 / 10
497. A Pseudo-Bayesian Algorithm for Robust PCA
Tae-Hyun Oh, Yasuyuki Matsushita, In So Kweon, David Wipf
Neural Information Processing Systems (NIPS) 2016 / 12
496. Refining Geometry from Depth Sensors using IR Shading Images
Gyeongmin Choe, Jaesik Park, Yu-Wing Tai, In So Kweon
International Journal of Computer Vision (IJCV) 2016 / 09
495. Natural Image Matting using Deep Convolutional Neural Networks
Donghyeon Cho, Yu-Wing Tai, In So Kweon
European Conference on Computer Vision (ECCV), 2016 2016 / 10
494. Photometric Stereo under Non-uniform Light Intensities and Exposures
Donghyeon Cho, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon
European Conference on Computer Vision (ECCV), 2016 2016 / 10
493. Fine-scale Surface Normal Estimation using a Single NIR Image
Youngjin Yoon, Gyeongmin Choe, Namil Kim, Joon-Young Lee, In So Kweon
European Conference on Computer Vision (ECCV) , October 2016 2016 / 10
492. All-around Depth from Small Motion with A Spherical Panoramic Camera
Sunghoon Im, Hyowon Ha, Francois Rameau, Hae-Gon Jeon, Gyeongmin Choe, In So Kweon
European Conference on Computer Vision (ECCV) 2016 / 10
491. Human Body Part Classification from Optical Flow
Junsik Kim, Kyungdon Joo, Tae-Hyun Oh, In So Kweon
The International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2016 / 08
490. Asymmetric Stereo with Catadioptric Lens: High Quality Image Generation for Intelligent Robot
Donghyeon Cho, Jinsun Park, Yu-Wing Tai, In So Kweon
The International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2016 / 08
489. Sentence Learning on Deep Convolutional Networks for Image Caption Generation
Dong-Jin Kim, Donggeun Yoo, Bonggeun Sim, In So Kweon
The International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2016 / 08
488. EureCar Turbo: a Self-Driving Car that can Handle Adverse Weather Conditions
Unghui Lee, Jiwon Jung, Seunghak Shin, Yongseop Jeong, Kibaek Park, David Hyunchul Shim, In So Kweon
The International Conference of Intelligent Robots and Systems (IROS) 2016 / 10
487. Object Proposal Using 3D Point Cloud for DRC-HUBO+
Seunghak Shin, Inwook Shim, Jiyoung Jung, Yunsu Bok, Jun-Ho Oh, In So Kweon
The International Conference of Intelligent Robots and Systems (IROS) 2016 / 10
486. Fast Multiple Objects Detection and Tracking Fusing Color Camera and 3D LIDAR for Intelligent Vehicles
Soonmin Hwang, Namil Kim, Yukyung Choi, Seokju Lee, In So Kweon
The International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2016 / 08
1
485. Thermal Image Enhancement using Convolution Neural Network
Yukyung Choi, Namil Kim, Soonmin Hwang, In So Kweon
The International Conference of Intelligent Robots and Systems (IROS) 2016 / 10
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 ... 31 Next
/ 31