Diffusion models for 3D generation: A survey  

作　　者：Chen Wang Hao-Yang Peng Ying-Tian Liu Jiatao Gu Shi-Min Hu 

机构地区：[1]Department of Computer and Information Science,University of Pennsylvania,Philadelphia,Pennsylvania 19104,USA [2]Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China [3]Machine Learning Research,Apple AI/ML,New York,USA.E-mail:[e-mail]

出　　处：《Computational Visual Media》2025年第1期1-28,共28页计算可视媒体(英文版)

摘　　要：Denoising diffusion models have demonstrated tremendous success in modeling data distributions and synthesizing high-quality samples.In the 2D image domain,they have become the state-of-the-art and are capable of generating photo-realistic images with high controllability.More recently,researchers have begun to explore how to utilize diffusion models to generate 3D data,as doing so has more potential in real-world applications.This requires careful design choices in two key ways:identifying a suitable 3D representation and determining how to apply the diffusion process.In this survey,we provide the first comprehensive review of diffusion models for manipulating 3D content,including 3D generation,reconstruction,and 3D-aware image synthesis.We classify existing methods into three major categories:2D space diffusion with pretrained models,2D space diffusion without pretrained models,and 3D space diffusion.We also summarize popular datasets used for 3D generation with diffusion models.Along with this survey,we maintain a repository https://github.com/cwchenwang/awesome-3d-diffusion to track the latest relevant papers and codebases.Finally,we pose current challenges for diffusion models for 3D generation,and suggest future research directions.

关 键 词：diffusion models 3D generation generative models AIG 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]