中文
相关论文

相关论文: StreamGVE: Training-Free Video Editing via Few-Ste…

200 篇论文

Video moment retrieval (VMR) aims to locate the most likely video moment(s) corresponding to a text query in untrimmed videos. Training of existing methods is limited by the lack of diverse and generalisable VMR datasets, hindering their…

计算机视觉与模式识别 · 计算机科学 2025-02-24 Dezhao Luo , Shaogang Gong , Jiabo Huang , Hailin Jin , Yang Liu

Recent advances in image editing, driven by image diffusion models, have shown remarkable progress. However, significant challenges remain, as these models often struggle to follow complex edit instructions accurately and frequently…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Noam Rotstein , Gal Yona , Daniel Silver , Roy Velich , David Bensaïd , Ron Kimmel

We present a novel task called online video editing, which is designed to edit \textbf{streaming} frames while maintaining temporal consistency. Unlike existing offline video editing assuming all frames are pre-established and accessible,…

计算机视觉与模式识别 · 计算机科学 2024-05-31 Feng Chen , Zhen Yang , Bohan Zhuang , Qi Wu

We introduce a novel pipeline for joint audio-visual editing that enhances the coherence between edited video and its accompanying audio. Our approach first applies state-of-the-art video editing techniques to produce the target video, then…

多媒体 · 计算机科学 2026-03-18 Masato Ishii , Akio Hayakawa , Takashi Shibuya , Yuki Mitsufuji

The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we…

计算机视觉与模式识别 · 计算机科学 2023-11-21 Michal Geyer , Omer Bar-Tal , Shai Bagon , Tali Dekel

Traditional video steganography methods are based on modifying the covert space for embedding, whereas we propose an innovative approach that embeds secret message within semantic feature for steganography during the video editing process.…

计算机视觉与模式识别 · 计算机科学 2024-01-02 Xueying Mao , Xiaoxiao Hu , Wanli Peng , Zhenliang Gan , Qichao Ying , Zhenxing Qian , Sheng Li , Xinpeng Zhang

While generative video models have achieved remarkable fidelity and consistency, applying these capabilities to video editing remains a complex challenge. Recent research has explored motion controllability as a means to enhance…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Ryan Burgert , Charles Herrmann , Forrester Cole , Michael S Ryoo , Neal Wadhwa , Andrey Voynov , Nataniel Ruiz

Generative models have demonstrated remarkable capability in synthesizing high-quality text, images, and videos. For video generation, contemporary text-to-video models exhibit impressive capabilities, crafting visually stunning videos.…

The field of video generation has made remarkable advancements, yet there remains a pressing need for a clear, systematic recipe that can guide the development of robust and scalable models. In this work, we present a comprehensive study…

The rising popularity of immersive visual experiences has increased interest in stereoscopic 3D video generation. Despite significant advances in video synthesis, creating 3D videos remains challenging due to the relative scarcity of 3D…

计算机视觉与模式识别 · 计算机科学 2025-05-02 Michal Geyer , Omer Tov , Linyi Jin , Richard Tucker , Inbar Mosseri , Tali Dekel , Noah Snavely

We tackle the long video generation problem, i.e.~generating videos beyond the output length of video generation models. Due to the computation resource constraints, video generation models can only generate video clips that are relatively…

计算机视觉与模式识别 · 计算机科学 2023-04-18 Hsin-Ping Huang , Yu-Chuan Su , Ming-Hsuan Yang

The rapid advancement in visual generation, particularly the emergence of pre-trained text-to-image and text-to-video models, has catalyzed growing interest in training-free video editing research. Mirroring training-free image editing…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Lianghan Zhu , Yanqi Bao , Jing Huo , Jing Wu , Yu-Kun Lai , Wenbin Li , Yang Gao

Diffusion-based or flow-based models have achieved significant progress in video synthesis but require multiple iterative sampling steps, which incurs substantial computational overhead. While many distillation methods that are solely based…

计算机视觉与模式识别 · 计算机科学 2025-09-18 Yanxiao Sun , Jiafu Wu , Yun Cao , Chengming Xu , Yabiao Wang , Weijian Cao , Donghao Luo , Chengjie Wang , Yanwei Fu

Diffusion models have revolutionized text-driven video editing. However, applying these methods to real-world editing encounters two significant challenges: (1) the rapid increase in GPU memory demand as the number of frames grows, and (2)…

计算机视觉与模式识别 · 计算机科学 2024-03-12 Shuzhou Yang , Chong Mou , Jiwen Yu , Yuhan Wang , Xiandong Meng , Jian Zhang

We introduce Emu Video Edit (EVE), a model that establishes a new state-of-the art in video editing without relying on any supervised video editing data. To develop EVE we separately train an image editing adapter and a video generation…

计算机视觉与模式识别 · 计算机科学 2024-03-26 Uriel Singer , Amit Zohar , Yuval Kirstain , Shelly Sheynin , Adam Polyak , Devi Parikh , Yaniv Taigman

We present an explicit-grid based method for efficiently reconstructing streaming radiance fields for novel view synthesis of real world dynamic scenes. Instead of training a single model that combines all the frames, we formulate the…

计算机视觉与模式识别 · 计算机科学 2022-10-27 Lingzhi Li , Zhen Shen , Zhongshu Wang , Li Shen , Ping Tan

Achieving streaming, fine-grained control over the outputs of autoregressive video diffusion models remains challenging, making it difficult to ensure that they consistently align with user expectations. To bridge this gap, we propose…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Junbao Zhou , Yuan Zhou , Kesen Zhao , Qingshan Xu , Beier Zhu , Richang Hong , Hanwang Zhang

We propose MLV-Edit, a training-free, flow-based framework that address the unique challenges of minute-level video editing. While existing techniques excel in short-form video manipulation, scaling them to long-duration videos remains…

计算机视觉与模式识别 · 计算机科学 2026-03-04 Yangyi Cao , Yuanhang Li , Lan Chen , Qi Mao

Understanding continuous video streams plays a fundamental role in real-time applications including embodied AI and autonomous driving. Unlike offline video understanding, streaming video understanding requires the ability to process video…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Yibin Yan , Jilan Xu , Shangzhe Di , Yikun Liu , Yudi Shi , Qirui Chen , Zeqian Li , Yifei Huang , Weidi Xie

Streaming free-viewpoint video~(FVV) in real-time still faces significant challenges, particularly in training, rendering, and transmission efficiency. Harnessing superior performance of 3D Gaussian Splatting~(3DGS), recent 3DGS-based FVV…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Zhihui Ke , Yuyang Liu , Xiaobo Zhou , Tie Qiu