基于符号距离函数的体渲染表面重建研究综述  

Review of research on volume rendering surface reconstruction based on signed distance function

在线阅读下载全文

作  者:余瑛 万贻前[1] 洪瀚 叶青 Yu Ying;Wan Yiqian;Hong Han;Ye Qing(School of Computer Science,Jiangxi University of Chinese Medicine,Nanchang 330004,China;Key Laboratory of Artificial Intelligence in Chinese Medicine,Jiangxi University of Chinese Medicine,Nanchang 330004,China)

机构地区:[1]江西中医药大学计算机学院,南昌330004 [2]江西中医药大学中医人工智能重点研究室,南昌330004

出  处:《计算机应用研究》2024年第12期3533-3542,共10页Application Research of Computers

基  金:江西中医药大学校级科技创新团队发展计划资助项目(CXTD22015)。

摘  要:在计算机视觉和图形学领域,多视图物体表面重建是一个重要的研究方向。符号距离函数的体渲染技术是一种新兴的物体表面重建方法,因其在复杂场景重建中的出色表现受到人们广泛关注。旨在对符号距离函数的体渲染技术进行全面分析和总结,为未来研究人员提供参考。首先介绍了有向符号距离函数的基本原理及其在体渲染技术中的应用;随后,从提升表面重建质量、加快训练速度、稀疏视图重建、重光照和材料编辑、特定场景重建等方面整理分析了该领域的关键模型改进和技术进展;此外,还对比分析了不同模型在速度和性能方面的表现,并简要介绍了模型评估的主要指标和公开数据集;最后,对该领域的研究现状进行了总结,并对未来的研究前景进行了展望和探讨。In the fields of computer vision and graphics,multi-view object surface reconstruction is a significant research direction.SDF volume rendering,as an emerging method for object surface reconstruction,garners widespread attention due to its outstanding performance in reconstructing complex scenes.This study provided a comprehensive analysis and summary of SDF volume rendering techniques,serving as a reference for future researchers.Firstly,this paper introduced the fundamental principles of directed SDF and its application in volume rendering technology.Subsequently,it organized and analyzed key model improvements and technological advancements in areas such as enhancing surface reconstruction quality,accelerating training speed,sparse view reconstruction,relighting,and material editing,as well as specific scene reconstruction.Additio-nally,this paper compared the speed and performance of different models and briefly introduced the main evaluation metrics and publicly available datasets.Finally,it summarized the current research status in this field,discussed and explored the future research prospects.

关 键 词:符号距离函数 体渲染技术 物体表面重建 

分 类 号:TP391.9[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象