中文
相关论文

相关论文: Movie Weaver: Tuning-Free Multi-Concept Video Pers…

200 篇论文

While there has been significant progress in customizing text-to-image generation models, generating images that combine multiple personalized concepts remains challenging. In this work, we introduce Concept Weaver, a method for composing…

计算机视觉与模式识别 · 计算机科学 2024-04-08 Gihyun Kwon , Simon Jenni , Dingzeyu Li , Joon-Young Lee , Jong Chul Ye , Fabian Caba Heilbron

Character image animation, which synthesizes videos of reference characters driven by pose sequences, has advanced rapidly but remains largely limited to single-human settings. Existing methods struggle to generalize to multi-humanoid…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Xirui Hu , Yanbo Ding , Jiahao Wang , Tingting Shi , Yali Wang , Guo Zhi Zhi , Weizhan Zhang

We present a method for multi-concept customization of pretrained text-to-video (T2V) models. Intuitively, the multi-concept customized video can be derived from the (non-linear) intersection of the video manifolds of the individual…

计算机视觉与模式识别 · 计算机科学 2024-05-24 Divya Kothandaraman , Kihyuk Sohn , Ruben Villegas , Paul Voigtlaender , Dinesh Manocha , Mohammad Babaeizadeh

Text-to-video generation has made remarkable advancements through diffusion models. However, Multi-Concept Video Customization (MCVC) remains a significant challenge. We identify two key challenges for this task: 1) the identity decoupling…

计算机视觉与模式识别 · 计算机科学 2025-05-14 Yuzhou Huang , Ziyang Yuan , Quande Liu , Qiulin Wang , Xintao Wang , Ruimao Zhang , Pengfei Wan , Di Zhang , Kun Gai

Current video generation models perform well at single-shot synthesis but struggle with multi-shot videos, facing critical challenges in maintaining character and background consistency across shots and flexibly generating videos of…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Xiangyang Luo , Qingyu Li , Xiaokun Liu , Wenyu Qin , Miao Yang , Meng Wang , Pengfei Wan , Di Zhang , Kun Gai , Shao-Lun Huang

Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity preservation from a…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Guocheng Gordon Qian , Daniil Ostashev , Egor Nemchinov , Avihay Assouline , Sergey Tulyakov , Kuan-Chieh Jackson Wang , Kfir Aberman

Text-driven video generation witnesses rapid progress. However, merely using text prompts is not enough to depict the desired subject appearance that accurately aligns with users' intents, especially for customized content creation. In this…

计算机视觉与模式识别 · 计算机科学 2023-12-04 Yuming Jiang , Tianxing Wu , Shuai Yang , Chenyang Si , Dahua Lin , Yu Qiao , Chen Change Loy , Ziwei Liu

The customization of text-to-image models has seen significant advancements, yet generating multiple personalized concepts remains a challenging task. Current methods struggle with attribute leakage and layout confusion when handling…

计算机视觉与模式识别 · 计算机科学 2024-09-10 Zebin Yao , Fangxiang Feng , Ruifan Li , Xiaojie Wang

Integrating multiple personalized concepts into a single image has recently gained attention in text-to-image (T2I) generation. However, existing methods often suffer from performance degradation in complex scenes due to distortions in…

计算机视觉与模式识别 · 计算机科学 2025-07-17 Young Beom Woo , Sun Eung Kim , Seong-Whan Lee

Visual concept composition, which aims to integrate different elements from images and videos into a single, coherent visual output, still falls short in accurately extracting complex concepts from visual inputs and flexibly combining…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Xianghao Kong , Zeyu Zhang , Yuwei Guo , Zhuoran Zhao , Songchun Zhang , Anyi Rao

Personalized text-to-image generation aims to synthesize images of user-provided concepts in diverse contexts. Despite recent progress in multi-concept personalization, most are limited to object concepts and struggle to customize abstract…

计算机视觉与模式识别 · 计算机科学 2026-02-23 Weizhi Zhong , Huan Yang , Zheng Liu , Huiguo He , Zijian He , Xuesong Niu , Di Zhang , Guanbin Li

In this work, we present a novel approach for motion customization in video generation, addressing the widespread gap in the exploration of motion representation within video generative models. Recognizing the unique challenges posed by the…

计算机视觉与模式识别 · 计算机科学 2024-10-18 Luozhou Wang , Ziyang Mai , Guibao Shen , Yixun Liang , Xin Tao , Pengfei Wan , Di Zhang , Yijun Li , Yingcong Chen

Video personalization methods allow us to synthesize videos with specific concepts such as people, pets, and places. However, existing methods often focus on limited domains, require time-consuming optimization per subject, or support only…

Current vision-language models (VLMs) show exceptional abilities across diverse tasks, such as visual question answering. To enhance user experience, recent studies investigate VLM personalization to understand user-provided concepts.…

计算机视觉与模式识别 · 计算机科学 2025-03-26 Ruichuan An , Sihan Yang , Ming Lu , Renrui Zhang , Kai Zeng , Yulin Luo , Jiajun Cao , Hao Liang , Ying Chen , Qi She , Shanghang Zhang , Wentao Zhang

Visual concept personalization aims to transfer only specific image attributes, such as identity, expression, lighting, and style, into unseen contexts. However, existing methods rely on holistic embeddings from general-purpose image…

Customized text-to-image generation, which synthesizes images based on user-specified concepts, has made significant progress in handling individual concepts. However, when extended to multiple concepts, existing methods often struggle with…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Jiaxiu Jiang , Yabo Zhang , Kailai Feng , Xiaohe Wu , Wenbo Li , Renjing Pei , Fan Li , Wangmeng Zuo

Text-to-image generation models have seen considerable advancement, catering to the increasing interest in personalized image creation. Current customization techniques often necessitate users to provide multiple images (typically 3-5) for…

计算机视觉与模式识别 · 计算机科学 2024-05-28 Linhao Zhong , Yan Hong , Wentao Chen , Binglin Zhou , Yiyi Zhang , Jianfu Zhang , Liqing Zhang

Video object insertion is a critical task for dynamically inserting new objects into existing environments. Previous video generation methods focus primarily on synthesizing entire scenes while struggling with ensuring consistent object…

计算机视觉与模式识别 · 计算机科学 2026-04-17 Xia Qi , Peishan Cong , Yichen Yao , Ziyi Wang , Yaoqin Ye , Yuexin Ma

Video personalization aims to generate videos that faithfully reflect a user-provided subject while following a text prompt. However, existing approaches often rely on heavy video-based finetuning or large-scale video datasets, which impose…

计算机视觉与模式识别 · 计算机科学 2025-12-16 Hyunkoo Lee , Wooseok Jang , Jini Yang , Taehwan Kim , Sangoh Kim , Sangwon Jung , Seungryong Kim

Customized text-to-video generation aims to generate high-quality videos guided by text prompts and subject references. Current approaches for personalizing text-to-video generation suffer from tackling multiple subjects, which is a more…

计算机视觉与模式识别 · 计算机科学 2025-10-29 Zhao Wang , Aoxue Li , Lingting Zhu , Yong Guo , Qi Dou , Zhenguo Li
‹ 上一页 1 2 3 10 下一页 ›