Score-based generative diffusion with "active" correlated noise sources
Diffusion models exhibit robust generative properties by approximating the underlying distribution of a dataset and synthesizing data by sampling from the approximated distribution. In this work, we explore how the generative performance may be be modulated if noise sources with temporal correlations -- akin to those used in the field of active matter -- are used for the destruction of the data in the forward process. Our numerical and analytical experiments suggest that the corresponding reverse process may exhibit improved generative properties.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
PTQD: Accurate Post-Training Quantization for Diffusion Models
Diffusion models have recently dominated image synthesis tasks. However, the iterative denoising process is expensive in computations at inference time, making diffusion models less practical for low-latency and scalable…
DenoisingImage GenerationQuantizationCARD: Correlation Aware Restoration with Diffusion
Denoising diffusion models have achieved state-of-the-art performance in image restoration by modeling the process as sequential denoising steps. However, most approaches assume independent and identically distributed (i…
Image RestorationGuided Trajectory Optimization with Sparse Scaling for Test-Time Diffusion
The efficient Test-Time Scaling (TTS) paradigm offers a promising perspective for enhancing the generation performance of diffusion models. However, current solutions are limited to a static, pre-defined noise pool and s…
Blue noise for diffusion models
Most of the existing diffusion models use Gaussian noise for training and sampling across all time steps, which may not optimally account for the frequency contents reconstructed by the denoising network. Despite the div…
DenoisingFrom Independent to Correlated Diffusion: Generalized Generative Modeling with Probabilistic Computers
Diffusion models have emerged as a powerful framework for generative tasks in deep learning. They decompose generative modeling into two computational primitives: deterministic neural-network evaluation and stochastic sa…