Multi-granularity relationship reasoning network for high-fidelity 3D shape reconstruction

doi:10.1016/j.patcog.2024.110647

	Multi-granularity relationship reasoning network for high-fidelity 3D shape reconstruction
	Li, Lei 1,2; Zhou, Zhiyuan 1,3; Wu, Suping 1; Li, Pan 1; Zhang, Boyang 1,4
	2024-11-01
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
卷号	155 页码:11
摘要	Monocular image -based 3D reconstruction is widely used in virtual reality, augmented reality, and autonomous driving, which benefits from the rapid development of deep learning approaches. Most of the available methods focused on reconstructing the overall shape of the object while ignoring some fine-grained details. Moreover, these methods make it hard to exactly reconstruct complex topological structures. In this paper, we propose a multi -granularity relationship reasoning network (MGRRNet), which aims to recover 3D shapes with high fidelity and rich details via the relationship reasoning between different granularity information. Specifically, our model captures the discriminative and detailed features at different granularities for extracting attentional regions. Then we perform the relationship reasoning between different granularities to reinforce the multi -granularity consistency and inter -granularity correlation. By doing this, our network is able to achieve robust feature representation and fine reconstruction. During the learning process, we jointly optimize procedures of different granularity feature representations via a sequence of inter -granularity cycle loss iterations. Extensive experimental results on two publicly available datasets justify that our approach achieves competitive performance compared to the state-of-the-art methods. Codes and all resources will be publicly available at https://github.com/Ray-tju/MGRRNet.
关键词	3D reconstruction Multi-granularity Cycle loss High-fidelity
DOI	10.1016/j.patcog.2024.110647
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62062056] ; Ningxia Graduate Education and Teaching Reform Research and Practice Project 2021
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001251884000001
出版者	ELSEVIER SCI LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39899
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wu, Suping
作者单位	1.Ningxia Univ, Sch Informat Engn, Yinchuan 750021, Peoples R China 2.Tongji Univ, Coll Elect & Informat Engn, Shanghai 201804, Peoples R China 3.Ningxia Med Univ, Gen Hosp, Yinchuan 750003, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing 101408, Peoples R China
推荐引用方式 GB/T 7714	Li, Lei,Zhou, Zhiyuan,Wu, Suping,et al. Multi-granularity relationship reasoning network for high-fidelity 3D shape reconstruction[J]. PATTERN RECOGNITION,2024,155:11.
APA	Li, Lei,Zhou, Zhiyuan,Wu, Suping,Li, Pan,&Zhang, Boyang.(2024).Multi-granularity relationship reasoning network for high-fidelity 3D shape reconstruction.PATTERN RECOGNITION,155,11.
MLA	Li, Lei,et al."Multi-granularity relationship reasoning network for high-fidelity 3D shape reconstruction".PATTERN RECOGNITION 155(2024):11.