Score-based Generative Models
Score-Based Generative Models is a class of generative modeling techniques within probabilistic machine learning that distinguishes itself by formulating the generation process through the estimation and inversion of score functions—gradients of the data density—to progressively denoise samples from a prior distribution back to the data manifold.
76
Publications
6K
Citations
285
Authors
93
Institutions
Publications per year
2017–2026
74
Variants
Score-based Generative ModelingScore-based Models
Parents
76
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
Haochen Wang, Xiaodan Du, Jiahao Li et al. · 2023 · 318 citations
Elucidating the Design Space of Diffusion-Based Generative Models
Tero Karras, Miika Aittala, Timo Aila et al. · arXiv (Cornell University) · 2022 · 308 citations · Full text
1–5 of 76
285
8
h-index
7
h-index
5
h-index
Korea Advanced Institute of Science and Technology, South Korea
3 publications · 33 citations
3
h-index
Korea Advanced Institute of Science and Technology, South Korea
3 publications · 33 citations
3
h-index
1–5 of 285
93
Stanford University
Stanford, United States
6 h-index
15 publications
3.4K citations
Nanchang University
Nanchang, China
5 h-index
27 publications
760 citations
Google (United States)
Mountain View, United States
4 h-index
12 publications
5.6K citations
Université de Montréal
Montreal, Canada
4 h-index
11 publications
261 citations
École Normale Supérieure - PSL
Paris, France
3 h-index
3 publications
58 citations
Département d'Informatique
Paris, France
3 h-index
3 publications
58 citations
University of California, Berkeley
Berkeley, United States
3 h-index
5 publications
170 citations
Intel (United States)
Santa Clara, United States
2 h-index
2 publications
101 citations
1–8 of 93
Repository · 38 publications · 3.9K citations
21
h-index
2 publications · 30 citations
2
h-index
3 publications · 141 citations
2
h-index
1 publications · 28 citations
1
h-index
1 publications · 22 citations
1
h-index
1–5