paper-with-me

홈 › Papers

MatchDiffusion: Training-free Generation of Match-cuts

2024-11-27 · Alejandro Pardo, Fabio Pizzati, Tong Zhang, Alexander Pondaven, Philip Torr, Juan Camilo Perez, Bernard Ghanem

Match-cuts are powerful cinematic tools that create seamless transitions between scenes, delivering strong visual and metaphorical connections. However, crafting match-cuts is a challenging, resource-intensive process requiring deliberate artistic planning. In MatchDiffusion, we present the first training-free method for match-cut generation using text-to-video diffusion models. MatchDiffusion leverages a key property of diffusion models: early denoising steps define the scene's broad structure, while later steps add details. Guided by this insight, MatchDiffusion employs "Joint Diffusion" to initialize generation for two prompts from shared noise, aligning structure and motion. It then applies "Disjoint Diffusion", allowing the videos to diverge and introduce unique details. This approach produces visually coherent videos suited for match-cuts. User studies and metrics demonstrate MatchDiffusion's effectiveness and potential to democratize match-cut creation.

📄 PDF Abstract BibTeX arXiv:2411.18677

Code (1)

PardoAlejo/MatchDiffusion 공식 구현 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

Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?

2024-11-25 · Sohee Yang, Nora Kassner, Elena Gribovskaya, Sebastian Riedel 외

We evaluate how well Large Language Models (LLMs) latently recall and compose facts to answer multi-hop queries like "In the year Scarlett Johansson was born, the Summer Olympics were hosted in the country of". One major…

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data

2026-04-20 · Zhenwen Liang, Yujun Zhou, Sidi Lu, Xiangliang Zhang 외 arxiv

Reinforcement Learning (RL) enhances LLM reasoning, yet a paradox emerges as models scale: strong base models saturate standard benchmarks (e.g., MATH), yielding correct but homogeneous solutions. In such environments, t…

Reinforcement LearningDomain Generalization

Joint Cuts and Matching of Partitions in One Graph

2017-11-27 · CVPR 2018 6 · Tianshu Yu, Junchi Yan, Jieyi Zhao, Baoxin Li

As two fundamental problems, graph cuts and graph matching have been investigated over decades, resulting in vast literature in these two topics respectively. However the way of jointly applying and solving graph cuts an…

Graph Matching

Paris 2.0: A Decentralized Diffusion Model for Video Generation

2026-05-25 · Ali Rouzbayani, Bidhan Roy, Marcos Villagra, Zhiying Jiang arxiv

We present Paris 2.0, the first video generation model pre-trained through decentralized computation. Its training recipe builds upon Paris 1.0 (arXiv:2510.03434), the first ever open-weight Decentralized Diffusion Model…

Video GenerationImage Generation

AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas

2026-03-16 · Longhui Yuan arxiv

Multi-person identity-preserving generation requires binding multiple reference faces to specified locations under a text prompt. Strong identity/layout conditions often trigger copy-paste shortcuts and weaken prompt-dri…

Image Generation