中文
相关论文

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

200 篇论文

We introduce Vid-CamEdit, a novel framework for video camera trajectory editing, enabling the re-synthesis of monocular videos along user-defined camera paths. This task is challenging due to its ill-posed nature and the limited multi-view…

Videos express highly structured spatio-temporal patterns of visual data. A video can be thought of as being governed by two factors: (i) temporally invariant (e.g., person identity), or slowly varying (e.g., activity), attribute-induced…

计算机视觉与模式识别 · 计算机科学 2018-03-26 Jiawei He , Andreas Lehrmann , Joseph Marino , Greg Mori , Leonid Sigal

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, this paper proposes a…

声音 · 计算机科学 2026-05-29 Maomao Li , Zhen Li , Kaipeng Zhang , Guosheng Yin , Zhifeng Li , Dong Xu

Recent text-to-video diffusion models have achieved impressive progress. In practice, users often desire the ability to control object motion and camera movement independently for customized video creation. However, current methods lack the…

计算机视觉与模式识别 · 计算机科学 2024-05-07 Shiyuan Yang , Liang Hou , Haibin Huang , Chongyang Ma , Pengfei Wan , Di Zhang , Xiaodong Chen , Jing Liao

Recently, text-to-image generation models have achieved remarkable advancements, particularly with diffusion models facilitating high-quality image synthesis from textual descriptions. However, these models often struggle with achieving…

计算机视觉与模式识别 · 计算机科学 2024-12-30 Lunhao Duan , Shanshan Zhao , Wenjun Yan , Yinglun Li , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang , Mingming Gong , Gui-Song Xia

Recent multimodal large language models have achieved strong performance in unified text and image understanding and generation, yet extending such native capability to 3D remains challenging due to limited data. Compared to abundant 2D…

计算机视觉与模式识别 · 计算机科学 2026-04-03 Chongjie Ye , Cheng Cao , Chuanyu Pan , Yiming Hao , Yihao Zhi , Yuanming Hu , Xiaoguang Han

Camera control has been extensively studied in conditioned video generation; however, performing precisely altering the camera trajectories while faithfully preserving the video content remains a challenging task. The mainstream approach to…

计算机视觉与模式识别 · 计算机科学 2026-02-02 Dong-Yu Chen , Yixin Guo , Shuojin Yang , Tai-Jiang Mu , Shi-Min Hu

Omnidirectional cameras are extensively used in various applications to provide a wide field of vision. However, they face a challenge in synthesizing novel views due to the inevitable presence of dynamic objects, including the…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Dongyoung Choi , Hyeonjoong Jang , Min H. Kim

Recent Vision-Language Models (VLMs) \textit{e.g.} CLIP have made great progress in video recognition. Despite the improvement brought by the strong visual backbone in extracting spatial features, CLIP still falls short in capturing and…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Mushui Liu , Bozheng Li , Yunlong Yu

Traditional and neural video codecs commonly encounter limitations in controllability and generality under ultra-low-bitrate coding scenarios. To overcome these challenges, we propose M3-CVC, a controllable video compression framework…

图像与视频处理 · 电气工程与系统科学 2024-12-30 Rui Wan , Qi Zheng , Yibo Fan

Camera-controllable image editing aims to synthesize novel views of a given scene under varying camera poses while strictly preserving cross-view geometric consistency. However, existing methods typically rely on fragmented geometric…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Hong Jiang , Wensong Song , Zongxing Yang , Ruijie Quan , Yi Yang

We introduce a framework that enables both multi-view character consistency and 3D camera control in video diffusion models through a novel customization data pipeline. We train the character consistency component with recorded volumetric…

We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to…

Significant progress has been made in audio-driven human animation, while most existing methods focus mainly on facial movements, limiting their ability to create full-body animations with natural synchronization and fluidity. They also…

计算机视觉与模式识别 · 计算机科学 2025-06-24 Qijun Gan , Ruizi Yang , Jianke Zhu , Shaofei Xue , Steven Hoi

Video generation has witnessed remarkable progress with the advent of deep generative models, particularly diffusion models. While existing methods excel in generating high-quality videos from text prompts or single images, personalized…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Yufan Deng , Xun Guo , Yizhi Wang , Jacob Zhiyuan Fang , Angtian Wang , Shenghai Yuan , Yiding Yang , Bo Liu , Haibin Huang , Chongyang Ma

Generating motion-controlled videos--where user-specified actions drive physically plausible scene dynamics under freely chosen viewpoints--demands two capabilities: (1) disentangled motion control, allowing users to separately control the…

计算机视觉与模式识别 · 计算机科学 2026-04-09 Shaowei Liu , Xuanchi Ren , Tianchang Shen , Huan Ling , Saurabh Gupta , Shenlong Wang , Sanja Fidler , Jun Gao

Real-world user-generated videos, especially on platforms like TikTok, often feature rich and intertwined audio visual content. However, existing video captioning benchmarks and models remain predominantly visual centric, overlooking the…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Peiran Wu , Yunze Liu , Zhengdong Zhu , Enmin Zhou , Junxiao Shen

Controllable generative models for images and videos have seen significant success, yet 3D scene generation, especially in unbounded scenarios like autonomous driving, remains underdeveloped. Existing methods lack flexible controllability…

计算机视觉与模式识别 · 计算机科学 2025-07-28 Ruiyuan Gao , Kai Chen , Zhihao Li , Lanqing Hong , Zhenguo Li , Qiang Xu

360{\deg} videos have emerged as a promising medium to represent our dynamic visual world. Compared to the "tunnel vision" of standard cameras, their borderless field of view offers a more complete perspective of our surroundings. While…

计算机视觉与模式识别 · 计算机科学 2026-04-24 Rundong Luo , Matthew Wallingford , Ali Farhadi , Noah Snavely , Wei-Chiu Ma

In this paper, we propose Universal Holistic Audio Generation (UniHAGen), a task for synthesizing comprehensive auditory scenes that include both on-screen and off-screen sounds across diverse domains (e.g., ambient events, musical…

声音 · 计算机科学 2026-04-07 Weiguo Pian , Saksham Singh Kushwaha , Zhimin Chen , Shijian Deng , Kai Wang , Yunhui Guo , Yapeng Tian