Generative Video Propagation
Shaoteng Liu, Tianyu Wang, Jui-Hsien Wang, Qing Liu, Zhifei Zhang, Joon-Young Lee, Yijun Li, Bei Yu, Zhe Lin, Soo Ye Kim, Jiaya Jia
摘要
Original Frame #1 Edited Frame #1 Input Video Frames (top) / Propagated by Ours (bottom) (b) Background Replacement (d) Object & Effect Tracking (e) Multiple Edits (a) Object & Effect Removal (c) Object Insertion 1 2 3 3 Figure 1. GenProp. We propose a generative video propagation framework (GenProp), which can seamlessly propagate any first frame edit through the video. GenProp supports a wide range of video applications, including (a) complete object removal with effects such as shadows and reflections, (b) background replacement with realistic effects, (c) object insertion where inserted objects have physically plausible motion (i.e., blueberries falling while spoon goes up), (d) tracking of objects and their associated effects, and (e) multiple edits (outpainting, insertion, removal) at a single inference run.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper23
- EditVerse: Unifying Image and Video Editing and Generation with In-Context LearningXuan Ju, Tianyu Wang, Yuqian Zhou, He Zhang 等ICLR 2026 · 被引用 56 次
- MiniMax-Remover: Taming Bad Noise Helps Video Object RemovalBojia Zi, Weixuan Peng, Xianbiao Qi, Jianan Wang 等NeurIPS 2025 · 被引用 43 次
- Unified In-Context Video EditingZixuan Ye, Xuanhua He, Quande Liu, Qiulin Wang 等ICLR 2026 · 被引用 37 次
- Generative Video Motion Editing with 3D Point TracksYao-Chih Lee, Zhoutong Zhang, Jiahui Huang, Jui-Hsien Wang 等CVPR 2026 · 被引用 23 次
- OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control ConditionsYuanhao Cai, He Zhang, Xi Chen, Jinbo Xing 等NeurIPS 2025 · 被引用 19 次
它引用的顶会 Paper26
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 被引用 6,759 次
- Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video GenerationJay Zhangjie Wu, Yixiao Ge, Xintao Wang, Stan Weixian Lei 等ICCV 2023 · 被引用 1,113 次
- FateZero: Fusing Attentions for Zero-shot Text-based Video EditingChenyang Qi, Xiaodong Cun, Yong Zhang, Chenyang Lei 等ICCV 2023 · 被引用 510 次
- Pix2Video: Video Editing using Image DiffusionDuygu Ceylan, Chun-Hao Paul Huang, Niloy J. MitraICCV 2023 · 被引用 370 次
相关 Paper
- Generative Omnimatte: Learning to Decompose Video into LayersYao-Chih Lee, Erika Lu, Sarah Rumbley, Michal Geyer 等CVPR 2025
- VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative PriorsJuil Koo, Paul Guerrero, Chun-Hao Paul Huang, Duygu Ceylan 等CVPR 2025
- FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video SynthesisFeng Liang, Bichen Wu, Jialiang Wang, Licheng Yu 等CVPR 2024
- SketchVideo: Sketch-based Video Generation and EditingFeng-Lin Liu, Hongbo Fu, Xintao Wang, Weicai Ye 等CVPR 2025
- MetaShadow: Object-Centered Shadow Detection, Removal, and SynthesisTianyu Wang, Jianming Zhang, Haitian Zheng, Zhihong Ding 等CVPR 2025
