paper-with-me

홈 › Papers

SyncSDE: A Probabilistic Framework for Diffusion Synchronization

2025-03-27 · CVPR 2025 1 · Hyunjun Lee, Hyunsoo Lee, Sookwan Han

There have been many attempts to leverage multiple diffusion models for collaborative generation, extending beyond the original domain. A prominent approach involves synchronizing multiple diffusion trajectories by mixing the estimated scores to artificially correlate the generation processes. However, existing methods rely on naive heuristics, such as averaging, without considering task specificity. These approaches do not clarify why such methods work and often produce suboptimal results when a heuristic suitable for one task is blindly applied to others. In this paper, we present a probabilistic framework for analyzing why diffusion synchronization works and reveal where heuristics should be focused; modeling correlations between multiple trajectories and adapting them to each specific task. We further identify optimal correlation models per task, achieving better results than previous approaches that apply a single heuristic across all tasks without justification.

📄 PDF Abstract BibTeX arXiv:2503.21555

Code (0)

등록된 구현이 없습니다.

Tasks

Specificity

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

Semantic Editing with Coupled Stochastic Differential Equations

2025-09-29 · Jianxin Zhang, Clayton Scott arxiv

Editing the content of an image with a pretrained text-to-image model remains challenging. Existing methods often distort fine details or introduce unintended artifacts. We propose using \emph{coupled stochastic differen…

Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors

2022-12-07 · ICCV 2023 1 · Zhentao Yu, Zixin Yin, Deyu Zhou, Duomin Wang 외

In this paper, we introduce a simple and novel framework for one-shot audio-driven talking head generation. Unlike prior works that require additional driving sources for controlled synthesis in a deterministic manner, w…

Talking Head Generation

Variational Test-time Optimization for Diffusion Synchronization

2026-06-14 · Hyunsoo Lee, Farrin Marouf Sofian, Kushagra Pandey, Stephan Mandt arxiv

Collaborative generation, which coordinates multiple diffusion trajectories to extend the capabilities of pretrained priors, has emerged as a powerful paradigm for extending the applicability of diffusion models. Among e…

Riemannian Functional Map Synchronization for Probabilistic Partial Correspondence in Shape Networks

2021-11-29 · Faria Huq, Adrish Dey, Sahra Yusuf, Dena Bazazian 외

We consider the problem of graph-matching on a network of 3D shapes with uncertainty quantification. We assume that the pairwise shape correspondences are efficiently represented as \emph{functional maps}, that match rea…

Graph MatchingUncertainty Quantification

SmoothSync: Dual-Stream Diffusion Transformers for Jitter-Robust Beat-Synchronized Gesture Generation from Quantized Audio

2026-01-04 · Yujiao Jiang, Qingmin Liao, Zongqing Lu arxiv

Co-speech gesture generation is a critical area of research aimed at synthesizing speech-synchronized human-like gestures. Existing methods often suffer from issues such as rhythmic inconsistency, motion jitter, foot sli…

Gesture Generation