On Diffusion Process in SE(3)-invariant Space
Not on the map. Why?
Abstract (arXiv)
Sampling viable 3D structures (e.g., molecules and point clouds) with SE(3)-invariance using diffusion-based models proved promising in a variety of real-world applications, wherein SE(3)-invariant properties can be naturally characterized by the inter-point distance manifold. However, due to the non-trivial geometry, we still lack a comprehensive understanding of the diffusion mechanism within such SE(3)-invariant space. This study addresses this gap by mathematically delineating the diffusion mechanism under SE(3)-invariance, via zooming into the interaction behavior between coordinates and the inter-point distance manifold through the lens of differential geometry. Upon this analysis, we propose accurate and projection-free diffusion SDE and ODE accordingly. Such formulations enable enhancing the performance and the speed of generation pathways; meanwhile offering valuable insights into other systems incorporating SE(3)-invariance.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 32 of its 50 references that are in the map. First posted on arXiv 3 Mar 2024.
Builds on
32 of 50 references.
References · 32
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2020Denoising Diffusion Implicit Modelscited by 9,655
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
- 2023Consistency Modelscited by 1,778
- 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
- 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
- 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
- 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
20 more
- 2020Directional Message Passing for Molecular Graphscited by 556
- 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
- 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
- 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
- 2022Torsional Diffusion for Molecular Conformer Generationcited by 262
- 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
- 2022Riemannian Score-Based Generative Modellingcited by 216
- 2023SE(3) diffusion model with application to protein backbone generationcited by 214
- 2021Learning Gradient Fields for Molecular Conformation Generationcited by 162
- 2019Learnable Triangulation of Human Posecited by 160
- 2023DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generationcited by 110
- 2021GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensemblescited by 106
- 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
- 2022Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Modelscited by 97
- 2021Learning Neural Generative Dynamics for Molecular Conformation Generationcited by 87
- 2023Generative Diffusion Models on Graphs: Methods and Applicationscited by 79
- 2022Direct Molecular Conformation Generationcited by 30
- 2019Generating valid Euclidean distance matricescited by 19
- 2023Learning to Decouple Complex Systemscited by 3
- 2023Molecular Conformation Generation via Shifting Scorescited by 2
Built on by
Citing papers per year: 2024: 1.
1 paper.
- 2024Generating Physical Dynamics under Priorscited by 6
- 2024Generating Physical Dynamics under Priors1 Sep 2024