Generalized Diffusion Model with Adjusted Offset Noise
Diffusion models have become fundamental tools for modeling data distributions in machine learning and have applications in image generation, drug discovery, and audio synthesis. Despite their success, these models face challenges when generating data with extreme brightness values, as evidenced by limitations in widely used frameworks like Stable Diffusion. Offset noise has been proposed as an empirical solution to this issue, yet its theoretical basis remains insufficiently explored. In this paper, we propose a generalized diffusion model that naturally incorporates additional noise within a rigorous probabilistic framework. Our approach modifies both the forward and reverse diffusion processes, enabling inputs to be diffused into Gaussian distributions with arbitrary mean structures. We derive a loss function based on the evidence lower bound, establishing its theoretical equivalence to offset noise with certain adjustments, while broadening its applicability. Experiments on synthetic datasets demonstrate that our model effectively addresses brightness-related challenges and outperforms conventional methods in high-dimensional scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
Audio SynthesisDrug DiscoveryImage GenerationmodelMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Reflection coupling for unadjusted generalized Hamiltonian Monte Carlo in the nonconvex stochastic gradient case
Contraction in Wasserstein 1-distance with explicit rates is established for generalized Hamiltonian Monte Carlo with stochastic gradients under possibly nonconvex conditions. The algorithms considered include splitting …
Noise Matters: Optimizing Matching Noise for Diffusion Classifiers
Although today's pretrained discriminative vision-language models (e.g., CLIP) have demonstrated strong perception abilities, such as zero-shot image classification, they also suffer from the bag-of-words problem and spu…
Zero-Shot Image ClassificationDenoising Diffusions with Optimal Transport: Localization, Curvature, and Multi-Scale Complexity
Adding noise is easy; what about denoising? Diffusion is easy; what about reverting a diffusion? Diffusion-based generative models aim to denoise a Langevin diffusion chain, moving from a log-concave equilibrium measure …
DenoisingMetropolis-Adjusted Diffusion Models
Sampling from score-based diffusion models incurs bias due to both time discretisation and the approximation of the score function. A common strategy for reducing this bias is to apply corrector steps based on the unadju…
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
Standard diffusion models involve an image transform -- adding Gaussian noise -- and an image restoration operator that inverts this degradation. We observe that the generative behavior of diffusion models is not strongl…
Image RestorationVariational Inference