中文
相关论文

相关论文: UniVideo: Unified Understanding, Generation, and E…

200 篇论文

Notable breakthroughs in unified understanding and generation modeling have led to remarkable advancements in image understanding, reasoning, production and editing, yet current foundational models predominantly focus on processing images,…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Zhiyu Tan , Hao Yang , Luozheng Qin , Jia Gong , Mengping Yang , Hao Li

Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. This stems from insufficient cross-modal interaction and…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Jiehui Huang , Yuechen Zhang , Xu He , Yuan Gao , Zhi Cen , Bin Xia , Yan Zhou , Xin Tao , Pengfei Wan , Jiaya Jia

With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing…

计算机视觉与模式识别 · 计算机科学 2020-09-16 Huaishao Luo , Lei Ji , Botian Shi , Haoyang Huang , Nan Duan , Tianrui Li , Jason Li , Taroon Bharti , Ming Zhou

Unified video modeling that combines generation and understanding capabilities is increasingly important but faces two key challenges: maintaining semantic faithfulness during flow-based generation due to text-visual token imbalance and the…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Jiabin Luo , Junhui Lin , Zeyu Zhang , Biao Wu , Meng Fang , Ling Chen , Hao Tang

The creation of diverse and realistic driving scenarios has become essential to enhance perception and planning capabilities of the autonomous driving system. However, generating long-duration, surround-view consistent driving videos…

计算机视觉与模式识别 · 计算机科学 2025-03-07 Rui Chen , Zehuan Wu , Yichen Liu , Yuxin Guo , Jingcheng Ni , Haifeng Xia , Siyu Xia

Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each problem setting, which fixes the input-output mapping and…

计算机视觉与模式识别 · 计算机科学 2026-05-04 Houyuan Chen , Hong Li , Xianghao Kong , Tianrui Zhu , Shaocong Xu , Weiqing Xiao , Yuwei Guo , Chongjie Ye , Lvmin Zhang , Hao Zhao , Anyi Rao

With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most…

计算机视觉与模式识别 · 计算机科学 2025-10-10 Chong Mou , Qichao Sun , Yanze Wu , Pengze Zhang , Xinghui Li , Fulong Ye , Songtao Zhao , Qian He

Unified multimodal models integrating visual understanding and generation face a fundamental challenge: visual generation incurs substantially higher computational costs than understanding, particularly for video. This imbalance motivates…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Luozheng Qin , Jia Gong , Qian Qiao , Tianjiao Li , Li Xu , Haoyu Pan , Chao Qu , Zhiyu Tan , Hao Li

Large language models, trained on extensive corpora, successfully unify diverse linguistic tasks within a single generative framework. Inspired by this, recent works like Large Vision Model (LVM) extend this paradigm to vision by organizing…

计算机视觉与模式识别 · 计算机科学 2025-09-29 Lan Chen , Yuchao Gu , Qi Mao

In this paper, we propose UniLIP, a unified framework that adapts CLIP for multimodal understanding, generation and editing. Although CLIP excels at understanding, it lacks reconstruction abilities required to be a unified visual encoder.…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Hao Tang , Chenwei Xie , Xiaoyi Bao , Tingyu Weng , Pandeng Li , Yun Zheng , Liwei Wang

Although a video is effectively a sequence of images, visual perception systems typically model images and videos separately, thus failing to exploit the correlation and the synergy provided by these two media. While a few prior research…

计算机视觉与模式识别 · 计算机科学 2019-06-13 Yufei Wang , Du Tran , Lorenzo Torresani

We present UniModel, a unified generative model that jointly supports visual understanding and visual generation within a single pixel-to-pixel diffusion framework. Our goal is to achieve unification along three axes: the model, the tasks,…

计算机视觉与模式识别 · 计算机科学 2025-11-24 Chi Zhang , Jiepeng Wang , Youming Wang , Yuanzhi Liang , Xiaoyan Yang , Zuoxin Li , Haibin Huang , Xuelong Li

Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream…

计算机视觉与模式识别 · 计算机科学 2021-12-16 Tianyi Liu , Zuxuan Wu , Wenhan Xiong , Jingjing Chen , Yu-Gang Jiang

The fashion domain encompasses a variety of real-world multimodal tasks, including multimodal retrieval and multimodal generation. The rapid advancements in artificial intelligence generated content, particularly in technologies like large…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Xiangyu Zhao , Yuehan Zhang , Wenlong Zhang , Xiao-Ming Wu

We present Omni-Video 2, a scalable and computationally efficient model that connects pretrained multimodal large-language models (MLLMs) with video diffusion models for unified video generation and editing. Our key idea is to exploit the…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Hao Yang , Zhiyu Tan , Jia Gong , Luozheng Qin , Hesen Chen , Xiaomeng Yang , Yuqing Sun , Yuetan Lin , Mengping Yang , Hao Li

Recent advances in text-guided video editing have showcased promising results in appearance editing (e.g., stylization). However, video motion editing in the temporal dimension (e.g., from eating to waving), which distinguishes video…

计算机视觉与模式识别 · 计算机科学 2024-04-09 Jianhong Bai , Tianyu He , Yuchi Wang , Junliang Guo , Haoji Hu , Zuozhu Liu , Jiang Bian

With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existing works are limited to specialized video understanding…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Hewen Pan , Cong Wei , Dashuang Liang , Zepeng Huang , Pengfei Gao , Ziqi Zhou , Lulu Xue , Pengfei Yan , Xiaoming Wei , Minghui Li , Shengshan Hu

We introduce UniReal, a unified framework designed to address various image generation and editing tasks. Existing solutions often vary by tasks, yet share fundamental principles: preserving consistency between inputs and outputs while…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Xi Chen , Zhifei Zhang , He Zhang , Yuqian Zhou , Soo Ye Kim , Qing Liu , Yijun Li , Jianming Zhang , Nanxuan Zhao , Yilin Wang , Hui Ding , Zhe Lin , Hengshuang Zhao

While the recent advances in Multimodal Large Language Models (MLLMs) constitute a significant leap forward in the field, these models are predominantly confined to the realm of input-side multimodal comprehension, lacking the capacity for…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Zhanyu Wang , Longyue Wang , Zhen Zhao , Minghao Wu , Chenyang Lyu , Huayang Li , Deng Cai , Luping Zhou , Shuming Shi , Zhaopeng Tu

In this paper, we propose \textbf{UniCode}, a novel approach within the domain of multimodal large language models (MLLMs) that learns a unified codebook to efficiently tokenize visual, text, and potentially other types of signals. This…

计算机视觉与模式识别 · 计算机科学 2024-03-15 Sipeng Zheng , Bohan Zhou , Yicheng Feng , Ye Wang , Zongqing Lu
‹ 上一页 1 2 3 10 下一页 ›