UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing

• URL: http://arxiv.org/abs/2402.13185v4
• Date: Sun, 7 Apr 2024 12:11:28 GMT
• Title: UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing
• Authors: Jianhong Bai, Tianyu He, Yuchi Wang, Junliang Guo, Haoji Hu, Zuozhu Liu, Jiang Bian,
• Abstract summary: We present UniEdit, a tuning-free framework that supports both video motion and appearance editing. To realize motion editing while preserving source video content, we introduce auxiliary motion-reference and reconstruction branches. The obtained features are then injected into the main editing path via temporal and spatial self-attention layers.
• Score: 28.140945021777878
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in text-guided video editing have showcased promising results in appearance editing (e.g., stylization). However, video motion editing in the temporal dimension (e.g., from eating to waving), which distinguishes video editing from image editing, is underexplored. In this work, we present UniEdit, a tuning-free framework that supports both video motion and appearance editing by harnessing the power of a pre-trained text-to-video generator within an inversion-then-generation framework. To realize motion editing while preserving source video content, based on the insights that temporal and spatial self-attention layers encode inter-frame and intra-frame dependency respectively, we introduce auxiliary motion-reference and reconstruction branches to produce text-guided motion and source features respectively. The obtained features are then injected into the main editing path via temporal and spatial self-attention layers. Extensive experiments demonstrate that UniEdit covers video motion editing and various appearance editing scenarios, and surpasses the state-of-the-art methods. Our code will be publicly available.

Related papers

• MagicStick: Controllable Video Editing via Control Handle Transformations [109.26314726025097]
  MagicStick is a controllable video editing method that edits the video properties by utilizing the transformation on the extracted internal control signals. We present experiments on numerous examples within our unified framework. We also compare with shape-aware text-based editing and handcrafted motion video generation, demonstrating our superior temporal consistency and editing capability than previous works.
  arXiv  Detail & Related papers  (2023-12-05T17:58:06Z)
• MotionEditor: Editing Video Motion via Content-Aware Diffusion [96.825431998349]
  MotionEditor is a diffusion model for video motion editing. It incorporates a novel content-aware motion adapter into ControlNet to capture temporal motion correspondence.
  arXiv  Detail & Related papers  (2023-11-30T18:59:33Z)
• FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing [65.60744699017202]
  We introduce optical flow into the attention module in the diffusion model's U-Net to address the inconsistency issue for text-to-video editing. Our method, FLATTEN, enforces the patches on the same flow path across different frames to attend to each other in the attention module. Results on existing text-to-video editing benchmarks show that our proposed method achieves the new state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-10-09T17:59:53Z)
• Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models [65.268245109828]
  Ground-A-Video is a video-to-video translation framework for multi-attribute video editing. It attains temporally consistent editing of input videos in a training-free manner. Experiments and applications demonstrate that Ground-A-Video's zero-shot capacity outperforms other baseline methods in terms of edit-accuracy and frame consistency.
  arXiv  Detail & Related papers  (2023-10-02T11:28:37Z)
• MagicProp: Diffusion-based Video Editing via Motion-aware Appearance Propagation [74.32046206403177]
  MagicProp disentangles the video editing process into two stages: appearance editing and motion-aware appearance propagation. In the first stage, MagicProp selects a single frame from the input video and applies image-editing techniques to modify the content and/or style of the frame. In the second stage, MagicProp employs the edited frame as an appearance reference and generates the remaining frames using an autoregressive rendering approach.
  arXiv  Detail & Related papers  (2023-09-02T11:13:29Z)
• MagicEdit: High-Fidelity and Temporally Coherent Video Editing [70.55750617502696]
  We present MagicEdit, a surprisingly simple yet effective solution to the text-guided video editing task. We found that high-fidelity and temporally coherent video-to-video translation can be achieved by explicitly disentangling the learning of content, structure and motion signals during training.
  arXiv  Detail & Related papers  (2023-08-28T17:56:22Z)
• Shape-aware Text-driven Layered Video Editing [39.56765973770167]
  We present a shape-aware, text-driven video editing method to handle shape changes. We first propagate the deformation field between the input and edited to all frames. We then leverage a pre-trained text-conditioned diffusion model as guidance for refining shape distortion and completing unseen regions.
  arXiv  Detail & Related papers  (2023-01-30T18:41:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.