3D object structure recovery via semi-supervised learning on videos

	3D object structure recovery via semi-supervised learning on videos
	He, Qian; Zhou, Desen; He, Xuming
	2019
会议录名称	29TH BRITISH MACHINE VISION CONFERENCE, BMVC 2018
发表状态	已发表
摘要	This paper addresses the problem of joint 3D object structure and camera pose estimation from a single RGB image. Existing approaches typically rely on both images with 2D keypoint annotations and 3D synthetic data to learn a deep network model due to difficulty in obtaining 3D annotations. However, the domain gap between the synthetic and image data usually leads to a 3D object interpretation model sensitive to the viewing angle, occlusion and background clutter in real images. In this work, we propose a semi-supervised learning strategy to build a robust 3D object interpreter, which exploits rich object videos for better generalization under large pose variations and noisy 2D keypoint estimation. The core design of our learning algorithm is a new loss function that enforces the temporal consistency constraint in the 3D predictions on videos. The experiment evaluation on the IKEA, PASCAL3D+ and our object video dataset shows that our approach achieves the state-of-the-art performance in structure and pose estimation. © 2018. The copyright of this document resides with its authors.
会议地点	Newcastle, United kingdom
收录类别	EI
出版者	BMVA Press
EI入藏号	20193807460284
EI主题词	Computer vision ; Learning algorithms ; Supervised learning
EI分类号	Computer Applications:723.5
原始文献类型	Conference article (CA)
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/29128
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_何旭明组信息科学与技术学院_博士生
作者单位	School of Information Science and Technology, ShanghaiTech University, Shanghai, China
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	He, Qian,Zhou, Desen,He, Xuming. 3D object structure recovery via semi-supervised learning on videos[C]:BMVA Press,2019.