Synthetic data generation by diffusion models

被引：0

作者：

Zhu, Jun ^{[1
,2
]}

机构：

[1] Tsinghua Univ, BNRist Ctr, Tsinghua Bosch Joint ML Ctr, Dept Comp Sci & Technol, Beijing, Peoples R China

[2] Pazhou Lab, Huangpu, Peoples R China

来源：

NATIONAL SCIENCE REVIEW | 2024年 / 11卷 / 08期

关键词：

D O I：

10.1093/nsr/nwae276

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

This paper provides a brief overview on diffusion models, which are extremely powerful on generating high-dimensional data, including images, 3D content, and videos, and provides insights for future work.

引用

页数：3

共 20 条

[1]

Bao F, 2024, Arxiv, DOI arXiv:2405.04233

[2]

Bao Fan., INT C LEARNING REPRE

[3]

Brooks Tim, 2024, Video generation models as world simulators

[4]

Chen H., INT C MACHINE LEARNI

[5]

Chen H., International Conference on Learning Representations, Kigali Rwanda, 1-5 May 2023

[6] Generative Adversarial Networks [J].

Goodfellow, Ian ;

Pouget-Abadie, Jean ;

Mirza, Mehdi ;

Xu, Bing ;

Warde-Farley, David ;

Ozair, Sherjil ;

Courville, Aaron ;

Bengio, Yoshua .

COMMUNICATIONS OF THE ACM, 2020, 63 (11) :139-144

[7]

Ho J., 2021, NEURIPS 2021 WORKSHO

[8]

Ho J., 2020, ADV NEURAL INFORM PR, P6840

[9]

Huang R., 2023, arXiv

[10]

Lu C., 2024, Proceedings of the 36th International Conference on Neural Information Processing Systems, P5775

← 1 2 →