標題: LEARNING POSE-AWARE 3D RECONSTRUCTION VIA 2D-3D SELF-CONSISTENCY
作者: Liao, Yi-Lun
Yang, Yao-Cheng
Lin, Yuan-Fang
Chen, Pin-Jung
Kuo, Chia-Wen
Chiu, Wei-Chen
Wang, Yu-Chiang Frank
資訊工程學系
Department of Computer Science
關鍵字: deep learning;3D shape reconstruction;camera pose estimation;perspective projection
公開日期: 1-Jan-2019
摘要: 3D reconstruction, inferring 3D shape information from a single 2D image, has drawn attention from learning and vision communities. In this paper, we propose a framework for learning pose-aware 3D shape reconstruction. Our proposed model learns deep representation for recovering the 3D object, with the ability to extract camera pose information but without any direct supervision of ground truth camera pose. This is realized by exploitation of 2D-3D self-consistency between 2D masks and 3D voxels. Experiments qualitatively and quantitatively demonstrate the effectiveness and robustness of our model, which performs favorably against state-of-the-art methods.
URI: http://hdl.handle.net/11536/152928
ISBN: 978-1-4799-8131-1
ISSN: 1520-6149
期刊: 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
起始頁: 3857
結束頁: 3861
Appears in Collections:Conferences Paper