Diffusion Probabilistic Fields
Diffusion probabilistic models have quickly become a major approach for generative modeling of images, 3D geometry, video and other domains. However, to adapt diffusion generative modeling to these domains the denoising network needs to be carefully designed for each domain independently, oftentimes under the assumption that data lives in a Euclidean grid. In this paper we introduce Diffusion Probabilistic Fields (DPF), a diffusion model that can learn distributions over continuous functions defined over metric spaces, commonly known as fields. We extend the formulation of diffusion probabilistic models to deal with this field parametrization in an explicit way, enabling us to define an end-to-end learning algorithm that side-steps the requirement of representing fields with latent vectors as in previous approaches (Dupont et al., 2022a; Du et al., 2021). We empirically show that, while using the same denoising network, DPF effectively deals with different modalities like 2D images and 3D geometry, in addition to modeling distributions over fields defined on non-Euclidean metric spaces.
Code (0)
등록된 구현이 없습니다.
Tasks
3D geometryDenoisingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models
Targeting to understand the underlying explainable factors behind observations and modeling the conditional generation process on these factors, we connect disentangled representation learning to Diffusion Probabilistic …
DisentanglementRepresentation LearningN-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting
Long-horizon wildfire risk forecasting requires generating probabilistic spatial fields under sparse event supervision while maintaining computational efficiency across multiple prediction horizons. Extending diffusion m…
Computational EfficiencyVector Field Synthesis with Sparse Streamlines Using Diffusion Model
We present a novel diffusion-based framework for synthesizing 2D vector fields from sparse, coherent inputs (i.e., streamlines) while maintaining physical plausibility. Our method employs a conditional denoising diffusio…
Probabilistic reconstruction of Dark Matter fields from biased tracers using diffusion models
Galaxies are biased tracers of the underlying cosmic web, which is dominated by dark matter components that cannot be directly observed. The relationship between dark matter density fields and galaxy distributions can be…
Sifting through the Noise: A Survey of Diffusion Probabilistic Models and Their Applications to Biomolecules
Diffusion probabilistic models have made their way into a number of high-profile applications since their inception. In particular, there has been a wave of research into using diffusion models in the prediction and desi…