paper-with-me

홈 › Papers

First Frame Is the Place to Go for Video Content Customization

2025-11-19 · Jingxi Chen, Zongxia Li, Zhichao Liu, Guangyao Shi, Xiyang Wu, Fuxiao Liu, Cornelia Fermuller, Brandon Y. Feng, Yiannis Aloimonos arxiv

What role does the first frame play in video generation models? Traditionally, it's viewed as the spatial-temporal starting point of a video, merely a seed for subsequent animation. In this work, we reveal a fundamentally different perspective: video models implicitly treat the first frame as a conceptual memory buffer that stores visual entities for later reuse during generation. Leveraging this insight, we show that it's possible to achieve robust and generalized video content customization in diverse scenarios, using only 20-50 training examples without architectural changes or large-scale finetuning. This unveils a powerful, overlooked capability of video generation models for reference-based video customization.

📄 PDF Abstract BibTeX arXiv:2511.15700

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization

2026-06-25 · Xuancheng Xu, Gengyun Jia, Bing-Kun Bao arxiv

Video customization based on Text-to-Video (T2V) models aims to learn specific features from reference data to generate controllable videos. While significant strides have been made in image stylization and video motion …

Text-to-Video Generation

MotionAdapter: Video Motion Transfer via Content-Aware Attention Customization

2026-01-05 · Zhexin Zhang, Yangyang Xu, Yifeng Zhu, Long Chen 외 arxiv

Recent advances in diffusion-based text-to-video models, particularly those built on the diffusion transformer architecture, have achieved remarkable progress in generating high-quality and temporally coherent videos. Ho…

OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model

2026-02-12 · Maomao Li, Zhen Li, Kaipeng Zhang, Guosheng Yin 외 arxiv

Existing mainstream video customization methods focus on generating identity-consistent videos based on given reference images and textual prompts. Benefiting from the rapid advancement of joint audio-video generation, t…

Contrastive LearningVideo Generation

MotionMatcher: Motion Customization of Text-to-Video Diffusion Models via Motion Feature Matching

2025-02-18 · Yen-Siang Wu, Chi-Pin Huang, Fu-En Yang, Yu-Chiang Frank Wang

Text-to-video (T2V) diffusion models have shown promising capabilities in synthesizing realistic videos from input text prompts. However, the input text description alone provides limited control over the precise objects…

DreamRelation: Relation-Centric Video Customization

2025-03-10 · Yujie Wei, Shiwei Zhang, Hangjie Yuan, Biao Gong 외

Relational video customization refers to the creation of personalized videos that depict user-specified relations between two subjects, a crucial task for comprehending real-world visual content. While existing methods c…

RelationTripletVideo Generation