paper-with-me

Papers

SyncTweedies: A General Generative Framework Based on Synchronized Diffusions

2024-03-21 · Jaihoon Kim, Juil Koo, Kyeongmin Yeo, Minhyuk Sung

We introduce a general framework for generating diverse visual content, including ambiguous images, panorama images, mesh textures, and Gaussian splat textures, by synchronizing multiple diffusion processes. We present exhaustive investigation into all possible scenarios for synchronizing multiple diffusion processes through a canonical space and analyze their characteristics across applications. In doing so, we reveal a previously unexplored case: averaging the outputs of Tweedie's formula while conducting denoising in multiple instance spaces. This case also provides the best quality with the widest applicability to downstream tasks. We name this case SyncTweedies. In our experiments generating visual content aforementioned, we demonstrate the superior quality of generation by SyncTweedies compared to other synchronization methods, optimization-based and iterative-update-based methods.

📄 PDF Abstract BibTeX arXiv:2403.14370

Code (1)

KAIST-Visual-AI-Group/SyncTweedies pytorch

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

From Denoising Diffusions to Denoising Markov Models

2022-11-07 · Joe Benton, Yuyang Shi, Valentin De Bortoli, George Deligiannidis 외

Denoising diffusions are state-of-the-art generative models exhibiting remarkable empirical performance. They work by diffusing the data distribution into a Gaussian distribution and then learning to reverse this noising…

Denoising

DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models

2023-05-25 · Yingqian Cui, Jie Ren, Han Xu, Pengfei He 외

Recently, Generative Diffusion Models (GDMs) have showcased their remarkable capabilities in learning and generating images. A large community of GDMs has naturally emerged, further promoting the diversified applications…

Generating from Discrete Distributions Using Diffusions: Insights from Random Constraint Satisfaction Problems

2026-03-21 · Alankrita Bhatt, Mukur Gupta, Germain Kolossov, Andrea Montanari arxiv

Generating data from discrete distributions is important for a number of application domains including text, tabular data, and genomic data. Several groups have recently used random $k$-satisfiability ($k$-SAT) as a synt…

SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions

2023-06-08 · NeurIPS 2023 11

The remarkable capabilities of pretrained image diffusion models have been utilized not only for generating fixed-size images but also for creating panoramas. However, naive stitching of multiple images often results in …

Conditional Image GenerationDenoisingImage Generation

Moment Estimate and Variational Approach for Learning Generalized Diffusion with Non-gradient Structures

2025-08-03 · Fanze Kong, Chen-Chih Lai, Yubin Lu arxiv

This paper proposes a data-driven learning framework for identifying governing laws of generalized diffusions with non-gradient components. By combining energy dissipation laws with a physically consistent penalty and fi…