中文
相关论文

相关论文: OmniCam: Unified Multimodal Video Generation via C…

200 篇论文

Urban scene synthesis with video generation models has recently shown great potential for autonomous driving. Existing video generation approaches to autonomous driving primarily focus on RGB video generation and lack the ability to support…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Guile Wu , David Huang , Dongfeng Bai , Bingbing Liu

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…

计算机视觉与模式识别 · 计算机科学 2022-06-10 Tim Brooks , Janne Hellsten , Miika Aittala , Ting-Chun Wang , Timo Aila , Jaakko Lehtinen , Ming-Yu Liu , Alexei A. Efros , Tero Karras

Recent advances in camera-controllable video generation have been constrained by the reliance on static-scene datasets with relative-scale camera annotations, such as RealEstate10K. While these datasets enable basic viewpoint control, they…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Guangcong Zheng , Teng Li , Xianpan Zhou , Xi Li

Human-centric motion control in video generation remains a critical challenge, particularly when jointly controlling camera movements and human poses in scenarios like the iconic Grammy Glambot moment. While recent video diffusion models…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Ruineng Li , Daitao Xing , Huiming Sun , Yuanzhou Ha , Jinglin Shen , Chiuman Ho

Egocentric video generation with fine-grained control through body motion is a key requirement towards embodied AI agents that can simulate, predict, and plan actions. In this work, we propose EgoControl, a pose-controllable video diffusion…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Enrico Pallotta , Sina Mokhtarzadeh Azar , Lars Doorenbos , Serdar Ozsoy , Umar Iqbal , Juergen Gall

Controllability, temporal coherence, and detail synthesis remain the most critical challenges in video generation. In this paper, we focus on a commonly used yet underexplored cinematic technique known as Frame In and Frame Out.…

计算机视觉与模式识别 · 计算机科学 2025-10-27 Boyang Wang , Xuweiyi Chen , Matheus Gadelha , Zezhou Cheng

Panoramic imagery, with its 360{\deg} field of view, offers comprehensive information to support Multi-Object Tracking (MOT) in capturing spatial and temporal relationships of surrounding objects. However, most MOT algorithms are tailored…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Kai Luo , Hao Shi , Sheng Wu , Fei Teng , Mengfei Duan , Chang Huang , Yuhang Wang , Kaiwei Wang , Kailun Yang

With the rise of diffusion models, audio-video generation has been revolutionized. However, most existing methods rely on separate modules for each modality, with limited exploration of unified generative architectures. In addition, many…

多媒体 · 计算机科学 2025-07-08 Lei Zhao , Linfeng Feng , Dongxu Ge , Rujin Chen , Fangqiu Yi , Chi Zhang , Xiao-Lei Zhang , Xuelong Li

Diffusion based video generation has received extensive attention and achieved considerable success within both the academic and industrial communities. However, current efforts are mainly concentrated on single-objective or single-task…

计算机视觉与模式识别 · 计算机科学 2024-01-18 Ludan Ruan , Lei Tian , Chuanwei Huang , Xu Zhang , Xinyan Xiao

Video generation models (VGMs) have received extensive attention recently and serve as promising candidates for general-purpose large vision models. While they can only generate short videos each time, existing methods achieve long video…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Yuanhui Huang , Wenzhao Zheng , Yuan Gao , Xin Tao , Pengfei Wan , Di Zhang , Jie Zhou , Jiwen Lu

Multi-camera 3D perception has emerged as a prominent research field in autonomous driving, offering a viable and cost-effective alternative to LiDAR-based solutions. The existing multi-camera algorithms primarily rely on monocular 2D…

计算机视觉与模式识别 · 计算机科学 2024-04-30 Chen Min , Liang Xiao , Dawei Zhao , Yiming Nie , Bin Dai

Given a video and a set of input object masks, an omnimatte method aims to decompose the video into semantically meaningful layers containing individual objects along with their associated effects, such as shadows and reflections. Existing…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Yao-Chih Lee , Erika Lu , Sarah Rumbley , Michal Geyer , Jia-Bin Huang , Tali Dekel , Forrester Cole

Modern multimodal large language models (MLLMs) generate fluent responses from interleaved text, image, audio, and video inputs. However, identifying which input sources support each generated statement remains an open challenge. Existing…

计算与语言 · 计算机科学 2026-04-16 Qianqi Yan , Yichen Guo , Ching-Chen Kuo , Shan Jiang , Hang Yin , Yang Zhao , Xin Eric Wang

Recent advances in video generation have led to remarkable improvements in visual quality and temporal coherence. Upon this, trajectory-controllable video generation has emerged to enable precise object motion control through explicitly…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Quanhao Li , Zhen Xing , Rui Wang , Hui Zhang , Qi Dai , Zuxuan Wu

Panoramic video generation has attracted growing attention due to its applications in virtual reality and immersive media. However, existing methods lack explicit motion control and struggle to generate scenes with large and complex…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Cheng Zhang , Hanwen Liang , Donny Y. Chen , Qianyi Wu , Konstantinos N. Plataniotis , Camilo Cruz Gambardella , Jianfei Cai

Recent advancements in audio-video joint generation models have demonstrated impressive capabilities in content creation. However, generating high-fidelity human-centric videos in complex, real-world physical scenes remains a significant…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Lei Zhu , Xing Cai , Yingjie Chen , Yiheng Li , Binxin Yang , Hao Liu , Jie Chen , Chen Li , Jing LYu

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

A unified diffusion framework for multi-modal generation and understanding has the transformative potential to achieve seamless and controllable image diffusion and other cross-modal tasks. In this paper, we introduce MMGen, a unified…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Jiepeng Wang , Zhaoqing Wang , Hao Pan , Yuan Liu , Dongdong Yu , Changhu Wang , Wenping Wang

Generating high-fidelity and controllable synthetic data is critical for advancing end-to-end autonomous driving, particularly for addressing the long tail of rare safety-critical scenarios. Existing occupancy-guided methods typically rely…

机器人学 · 计算机科学 2026-05-26 Haiming Zhang , Junfei Zhou , Feng Jiang , Jingzhong Li , Zhenglong Guo , Penglin Dai , Jifeng Dai , Yan Xie , Benjin Zhu

Despite significant advances in video synthesis, research into multi-shot video generation remains in its infancy. Even with scaled-up models and massive datasets, the shot transition capabilities remain rudimentary and unstable, largely…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Xiaoxue Wu , Bingjie Gao , Yu Qiao , Yaohui Wang , Xinyuan Chen