English
Related papers

Related papers: FullDiT: Multi-Task Video Generative Foundation Mo…

200 papers

Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Junpeng Jiang , Gangyi Hong , Miao Zhang , Hengtong Hu , Kun Zhan , Rui Shao , Liqiang Nie

Long-form video generation is rapidly moving from short, single-scene synthesis toward minute-long, multi-shot creation with narrative structure, cinematic control, audio, and cross-modal synchronization. However, evaluating such videos…

Computation and Language · Computer Science 2026-05-29 Jiamin Chen , Qianben Chen , Jiawen Zhang , Yidi Wu , Yuchen Li , Xiaokun Zhang , Wangchunshu Zhou , Chen Ma

With the rapid development of AI-generated content (AIGC), video generation has emerged as one of its most dynamic and impactful subfields. In particular, the advancement of video generation foundation models has led to growing demand for…

Generating multi-view videos for autonomous driving training has recently gained much attention, with the challenge of addressing both cross-view and cross-frame consistency. Existing methods typically apply decoupled attention mechanisms…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Hannan Lu , Xiaohe Wu , Shudong Wang , Xiameng Qin , Xinyu Zhang , Junyu Han , Wangmeng Zuo , Ji Tao

Recently, foundation models have exhibited remarkable advancements in multi-modal learning. These models, equipped with millions (or billions) of parameters, typically require a substantial amount of data for finetuning. However, collecting…

Machine Learning · Computer Science 2023-08-25 Haokun Chen , Yao Zhang , Denis Krompass , Jindong Gu , Volker Tresp

As Large Language Models (LLMs) are increasingly applied across various tasks, instruction tuning has emerged as a critical method for enhancing model performance. However, current data management strategies face substantial challenges in…

Computation and Language · Computer Science 2025-04-15 Yangning Li , Zihua Lan , Lv Qingsong , Yinghui Li , Hai-Tao Zheng

Real-world videos consist of sequences of events. Generating such sequences with precise temporal control is infeasible with existing video generators that rely on a single paragraph of text as input. When tasked with generating multiple…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Ziyi Wu , Aliaksandr Siarohin , Willi Menapace , Ivan Skorokhodov , Yuwei Fang , Varnith Chordia , Igor Gilitschenski , Sergey Tulyakov

We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Tim Brooks , Janne Hellsten , Miika Aittala , Ting-Chun Wang , Timo Aila , Jaakko Lehtinen , Ming-Yu Liu , Alexei A. Efros , Tero Karras

3D Human motion generation is pivotal across film, animation, gaming, and embodied intelligence. Traditional 3D motion synthesis relies on costly motion capture, while recent work shows that 2D videos provide rich, temporally coherent…

Graphics · Computer Science 2026-05-20 Yi-Yang Zhang , Tengjiao Sun , Pengcheng Fang , Deng-Bao Wang , Xiaohao Cai , Min-Ling Zhang , Hansung Kim

Efficient video generation models are increasingly vital for multimedia synthetic content generation. Leveraging the Transformer architecture and the diffusion process, video DiT models have emerged as a dominant approach for high-quality…

Graphics · Computer Science 2026-02-27 Yuanxin Wei , Lansong Diao , Bujiao Chen , Shenggan Cheng , Zhengping Qian , Wenyuan Yu , Nong Xiao , Wei Lin , Jiangsu Du

Video DiTs have advanced video generation, yet they still struggle to model multi-instance or subject-object interactions. This raises a key question: How do these models internally represent interactions? To answer this, we curate…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Siyoon Jin , Seongchan Kim , Dahyun Chung , Jaeho Lee , Hyunwook Choi , Jisu Nam , Jiyoung Kim , Seungryong Kim

Identity-preserving video generation offers powerful tools for creative expression, allowing users to customize videos featuring their beloved characters. However, prevailing methods are typically designed and optimized for a single…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Jiahao Wang , Hualian Sheng , Sijia Cai , Yuxiao Yang , Weizhan Zhang , Caixia Yan , Bing Deng , Jieping Ye

Conditional motion generation has been extensively studied in computer vision, yet two critical challenges remain. First, while masked autoregressive methods have recently outperformed diffusion-based approaches, existing masking models…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Zeyu Zhang , Yiran Wang , Wei Mao , Danning Li , Rui Zhao , Biao Wu , Zirui Song , Bohan Zhuang , Ian Reid , Richard Hartley

Diffusion models have made tremendous progress in text-driven image and video generation. Now text-to-image foundation models are widely applied to various downstream image synthesis tasks, such as controllable image generation and image…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 Fengyuan Shi , Jiaxi Gu , Hang Xu , Songcen Xu , Wei Zhang , Limin Wang

Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Andreas Blattmann , Robin Rombach , Huan Ling , Tim Dockhorn , Seung Wook Kim , Sanja Fidler , Karsten Kreis

In this paper, we study video synthesis with emphasis on simplifying the generation conditions. Most existing video synthesis models or datasets are designed to address complex motions of a single object, lacking the ability of…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Yang Wu , Zhibin Liu , Hefeng Wu , Liang Lin

DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored. In this work, we introduce a training-free approach to enhance the coherence and quality of DiT-based…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Yang Luo , Xuanlei Zhao , Mengzhao Chen , Kaipeng Zhang , Wenqi Shao , Kai Wang , Zhangyang Wang , Yang You

Generating 4D scenes from a single-view video is inherently ill-posed: a single viewpoint lacks the information needed to recover a complete, dynamic scene with full coverage. Existing methods are typically limited to monocular videos,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Tingxi Chen , Ke Hao , Yabo Chen , Zhengxue Cheng , Rong Xie , Li Song , Haibin Huang , Chi Zhang , Xuelong Li

A vast amount of instruction tuning data is crucial for the impressive performance of Large Multimodal Models (LMMs), but the associated computational costs and data collection demands during supervised fine-tuning make it impractical for…

Machine Learning · Computer Science 2025-07-22 Haiyang Guo , Fanhu Zeng , Fei Zhu , Wenzhuo Liu , Da-Han Wang , Jian Xu , Xu-Yao Zhang , Cheng-Lin Liu

Sora has unveiled the immense potential of the Diffusion Transformer (DiT) architecture in single-scene video generation. However, the more challenging task of multi-scene video generation, which offers broader applications, remains…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Tianhao Qi , Jianlong Yuan , Wanquan Feng , Shancheng Fang , Jiawei Liu , SiYu Zhou , Qian He , Hongtao Xie , Yongdong Zhang