Follow-Your-Creation: Empowering 4D Creation through Video Inpainting

• URL: http://arxiv.org/abs/2506.04590v1
• Date: Thu, 05 Jun 2025 03:11:48 GMT
• Title: Follow-Your-Creation: Empowering 4D Creation through Video Inpainting
• Authors: Yue Ma, Kunyu Feng, Xinhua Zhang, Hongyu Liu, David Junhao Zhang, Jinbo Xing, Yinhan Zhang, Ayden Yang, Zeyu Wang, Qifeng Chen,
• Abstract summary: Follow-Your-Creation is a framework capable of generating and editing 4D content from a single monocular video input.<n>By leveraging a powerful video inpainting foundation model as a generative prior, we reformulate 4D video creation as a video inpainting task.
• Score: 47.08187788419001
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce Follow-Your-Creation, a novel 4D video creation framework capable of both generating and editing 4D content from a single monocular video input. By leveraging a powerful video inpainting foundation model as a generative prior, we reformulate 4D video creation as a video inpainting task, enabling the model to fill in missing content caused by camera trajectory changes or user edits. To facilitate this, we generate composite masked inpainting video data to effectively fine-tune the model for 4D video generation. Given an input video and its associated camera trajectory, we first perform depth-based point cloud rendering to obtain invisibility masks that indicate the regions that should be completed. Simultaneously, editing masks are introduced to specify user-defined modifications, and these are combined with the invisibility masks to create a composite masks dataset. During training, we randomly sample different types of masks to construct diverse and challenging inpainting scenarios, enhancing the model's generalization and robustness in various 4D editing and generation tasks. To handle temporal consistency under large camera motion, we design a self-iterative tuning strategy that gradually increases the viewing angles during training, where the model is used to generate the next-stage training data after each fine-tuning iteration. Moreover, we introduce a temporal packaging module during inference to enhance generation quality. Our method effectively leverages the prior knowledge of the base model without degrading its original performance, enabling the generation of 4D videos with consistent multi-view coherence. In addition, our approach supports prompt-based content editing, demonstrating strong flexibility and significantly outperforming state-of-the-art methods in both quality and versatility.

Related papers

• Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion [52.0192865857058]
  We propose the first training-free 4D video generation method that leverages the off-the-shelf video diffusion models to generate multi-view videos from a single input video.<n>Our method is training-free and fully utilizes an off-the-shelf video diffusion model, offering a practical and effective solution for multi-view video generation.
  arXiv  Detail & Related papers  (2025-03-28T17:14:48Z)
• VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control [47.34885131252508]
  Video inpainting aims to restore corrupted video content.<n>We propose a novel dual-stream paradigm VideoPainter to process masked videos.<n>We also introduce a novel target region ID resampling technique that enables any-length video inpainting.
  arXiv  Detail & Related papers  (2025-03-07T17:59:46Z)
• MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow [15.155484662231508]
  We present MVTokenFlow for high-quality 4D content creation from monocular videos.<n>We utilize the multiview diffusion model to generate multiview images on different timesteps.<n>MVTokenFlow further regenerates all the multiview images using the rendered 2D flows as guidance.
  arXiv  Detail & Related papers  (2025-02-17T11:34:58Z)
• Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models [54.35214051961381]
  3D meshes are widely used in computer vision and graphics for their efficiency in animation and minimal memory use in movies, games, AR, and VR.<n>However, creating temporal consistent and realistic textures for mesh remains labor-intensive for professional artists.<n>We present 3D Tex sequences that integrates inherent geometry from mesh sequences with video diffusion models to produce consistent textures.
  arXiv  Detail & Related papers  (2024-10-14T17:59:59Z)
• Replace Anyone in Videos [82.37852750357331]
  We present the ReplaceAnyone framework, which focuses on localized human replacement and insertion featuring intricate backgrounds.<n>We formulate this task as an image-conditioned video inpainting paradigm with pose guidance, utilizing a unified end-to-end video diffusion architecture.<n>The proposed ReplaceAnyone can be seamlessly applied not only to traditional 3D-UNet base models but also to DiT-based video models such as Wan2.1.
  arXiv  Detail & Related papers  (2024-09-30T03:27:33Z)
• Blended Latent Diffusion under Attention Control for Real-World Video Editing [5.659933808910005]
  We propose to adapt a image-level blended latent diffusion model to perform local video editing tasks. Specifically, we leverage DDIM inversion to acquire the latents as background latents instead of the randomly noised ones. We also introduce an autonomous mask manufacture mechanism derived from cross-attention maps in diffusion steps.
  arXiv  Detail & Related papers  (2024-09-05T13:23:52Z)
• CT4D: Consistent Text-to-4D Generation with Animatable Meshes [53.897244823604346]
  We present a novel framework, coined CT4D, which directly operates on animatable meshes for generating consistent 4D content from arbitrary user-supplied prompts. Our framework incorporates a unique Generate-Refine-Animate (GRA) algorithm to enhance the creation of text-aligned meshes. Our experimental results, both qualitative and quantitative, demonstrate that our CT4D framework surpasses existing text-to-4D techniques in maintaining interframe consistency and preserving global geometry.
  arXiv  Detail & Related papers  (2024-08-15T14:41:34Z)
• Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models [40.71940056121056]
  We present a novel approach that combines the controllability of dynamic 3D meshes with the expressivity and editability of emerging diffusion models. We demonstrate our approach on various examples where motion can be obtained by animating rigged assets or changing the camera path.
  arXiv  Detail & Related papers  (2023-12-03T14:17:11Z)
• Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image [59.18564636990079]
  We study the problem of synthesizing a long-term dynamic video from only a single image. Existing methods either hallucinate inconsistent perpetual views or struggle with long camera trajectories. We present Make-It-4D, a novel method that can generate a consistent long-term dynamic video from a single image.
  arXiv  Detail & Related papers  (2023-08-20T12:53:50Z)

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.