计算机工程与应用2024，Vol.60Issue(4)：21-38,18.DOI:10.3778/j.issn.1002-8331.2303-0218
神经辐射场多视图合成技术综述
Survey of Neural Radiance Fields for Multi-View Synthesis Technologies
摘要
Abstract
Rendering realistic virtual scenes from images has been a long-standing research goal in the fields of computer graphics and computer vision.NeRF(neural radiance fields)is an emerging method based on deep neural networks,which achieves realistic rendering by learning the radiance field of each point in the scene.By using neural radiance fields,not only realistic images but also realistic three-dimensional scenes can be generated,making it have a wide range of application prospects such as virtual reality,augmented reality and computer games.However,its basic model has shortcomings such as low training efficiency,poor generalization ability,insufficient interpretability,susceptible to lighting and material changes,inability to handle dynamic scenes,and other deficiencies that may result in suboptimal rendering results in certain situations.With the continuous popularity of this field,a large amount of research has been carried out,yielding impressive results in terms of efficiency and accuracy.In order to track the latest research in this field,this paper provides a review and summary of the key algorithms in recent years.This paper first outlines the background and princi-ples of neural radiance fields,and briefly introduces the evaluation metrics and public datasets in this field.Then,a classi-fication discussion is conducted on the key improvements to the model,mainly including:the optimization of basic NeRF model parameters,the improvement in rendering speed and inference ability,the enhancement of spatial representation and lighting ability,the improvement in camera pose and sparse view synthesis methods for static scene,and the develop-ment in dynamic scene modeling field.Subsequently,the speed and performance of various models are classified,com-pared and analyzed,and the main model evaluation indicators and open datasets in this field are briefly introduced.Final-ly,the future development trend of neural radiance field is prospected.关键词
神经辐射场(NeRF)/视图合成/神经渲染/场景表达/深度学习/三维重建Key words
neural radiance fields(NeRF)/view synthesis/neural rendering/scene representation/deep learning/3D reconstruction分类
信息技术与安全科学引用本文复制引用
马汉声,祝玉华,李智慧,阎磊,司艺艺,连一萌,张钰涵..神经辐射场多视图合成技术综述[J].计算机工程与应用,2024,60(4):21-38,18.基金项目
国家重点研发计划(2022YFD2100202,2017YFD0401004,2018YFD0401404) （2022YFD2100202,2017YFD0401004,2018YFD0401404）
河南省科技攻关项目(202102110062). （202102110062）
