按年被提到
20232024 · 1 次2026
视觉、语音与图像生成›扩散模型·arXiv:2305.03486 · cs.GR

Iterative $α$-(de)Blending: a Minimalist Deterministic Diffusion Model

Eric Heitz, Laurent Belcour, Thomas Chambon · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-03-11 · 最近 2026-10-10
2不同的人
2活跃月份
2讨论串
17被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We derive a minimalist but powerful deterministic denoising-diffusion model. While denoising diffusion has shown great success in many domains, its underlying theory remains largely inaccessible to non-expert users. Indeed, an understanding of graduate-level concepts such as Langevin dynamics or score matching appears to be required to grasp how it works. We propose an alternative approach that requires no more than undergrad calculus and probability. We consider two densities and observe what happens when random samples from these densities are blended (linearly interpolated). We show that iteratively blending and deblending samples produces random paths between the two densities that converge toward a deterministic mapping. This mapping can be evaluated with a neural network trained to deblend samples. We obtain a model that behaves like deterministic denoising diffusion: it iteratively maps samples from one density (e.g., Gaussian noise) to another (e.g., cat images). However, compared to the state-of-the-art alternative, our model is simpler to derive, simpler to implement, more numerically stable, achieves higher quality results in our experiments, and has interesting connections to computer graphics.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论strangecasts · 2024-03

“Super interesting! Immediately reminded of Iterative alpha-(de)Blending [1] which also sets out to set up a conceptually simpler diffusion model, and also arrives at formulating it as an approximate iterative projection process - I think this approach allows for more interesting experiments like the denoiser error analysis, though. [1] https://arxiv.org…”

Diffusion models from scratch, from a new theoretical perspective原评论 ↗
评论stratos123 · 2026-10

“For more info on why flow-matching is more stable than DDIM, see Heitz 2023, which nicely explains how they're almost equivalent but DDIM corresponds to a differential equation with a 1/α term that diverges at the start of the denoising process, while flow-matching/IADB doesn't diverge: https://arxiv.org/abs/2305.03486”

Can you use autoregressive diffusion to generate market data?原评论 ↗