DiffuEraser: A Diffusion Model for Video Inpainting

• URL: http://arxiv.org/abs/2501.10018v1
• Date: Fri, 17 Jan 2025 08:03:02 GMT
• Title: DiffuEraser: A Diffusion Model for Video Inpainting
• Authors: Xiaowen Li, Haolan Xue, Peiran Ren, Liefeng Bo,
• Abstract summary: We introduce DiffuEraser, a video inpainting model based on stable diffusion, to fill masked regions with greater details and more coherent structures. We also expand the temporal receptive fields of both the prior model and DiffuEraser, and further enhance consistency by leveraging the temporal smoothing property of Video Diffusion Models.
• Score: 13.292164408616257
• License:
• Abstract: Recent video inpainting algorithms integrate flow-based pixel propagation with transformer-based generation to leverage optical flow for restoring textures and objects using information from neighboring frames, while completing masked regions through visual Transformers. However, these approaches often encounter blurring and temporal inconsistencies when dealing with large masks, highlighting the need for models with enhanced generative capabilities. Recently, diffusion models have emerged as a prominent technique in image and video generation due to their impressive performance. In this paper, we introduce DiffuEraser, a video inpainting model based on stable diffusion, designed to fill masked regions with greater details and more coherent structures. We incorporate prior information to provide initialization and weak conditioning,which helps mitigate noisy artifacts and suppress hallucinations. Additionally, to improve temporal consistency during long-sequence inference, we expand the temporal receptive fields of both the prior model and DiffuEraser, and further enhance consistency by leveraging the temporal smoothing property of Video Diffusion Models. Experimental results demonstrate that our proposed method outperforms state-of-the-art techniques in both content completeness and temporal consistency while maintaining acceptable efficiency.

Related papers

• VipDiff: Towards Coherent and Diverse Video Inpainting via Training-free Denoising Diffusion Models [21.584843961386888]
  VipDiff is a framework for conditioning diffusion model on the reverse diffusion process to produce temporal-coherent inpainting results. It can largely outperform state-of-the-art video inpainting methods in terms of both spatial-temporal coherence and fidelity.
  arXiv  Detail & Related papers  (2025-01-21T16:39:09Z)
• RepVideo: Rethinking Cross-Layer Representation for Video Generation [53.701548524818534]
  We propose RepVideo, an enhanced representation framework for text-to-video diffusion models. By accumulating features from neighboring layers to form enriched representations, this approach captures more stable semantic information. Our experiments demonstrate that our RepVideo not only significantly enhances the ability to generate accurate spatial appearances, but also improves temporal consistency in video generation.
  arXiv  Detail & Related papers  (2025-01-15T18:20:37Z)
• ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer [95.80384464922147]
  Continuous visual generation requires the full-sequence diffusion-based approach. We present ACDiT, an Autoregressive blockwise Conditional Diffusion Transformer. We demonstrate that ACDiT can be seamlessly used in visual understanding tasks despite being trained on the diffusion objective.
  arXiv  Detail & Related papers  (2024-12-10T18:13:20Z)
• Optical-Flow Guided Prompt Optimization for Coherent Video Generation [51.430833518070145]
  We propose a framework called MotionPrompt that guides the video generation process via optical flow. We optimize learnable token embeddings during reverse sampling steps by using gradients from a trained discriminator applied to random frame pairs. This approach allows our method to generate visually coherent video sequences that closely reflect natural motion dynamics, without compromising the fidelity of the generated content.
  arXiv  Detail & Related papers  (2024-11-23T12:26:52Z)
• Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Method [60.88467353578118]
  We show that a fixed-point-inspired iterative approach to invert real-world images does not achieve convergence, instead oscillating between distinct clusters. We introduce a simple and fast distribution transfer technique that facilitates image enhancement, stroke-based recoloring, as well as visual prompt-guided image editing.
  arXiv  Detail & Related papers  (2024-11-17T17:45:37Z)
• Video Diffusion Models are Strong Video Inpainter [14.402778136825642]
  We propose a novel First Frame Filling Video Diffusion Inpainting model (FFF-VDI) We propagate the noise latent information of future frames to fill the masked areas of the first frame's noise latent code. Next, we fine-tune the pre-trained image-to-video diffusion model to generate the inpainted video.
  arXiv  Detail & Related papers  (2024-08-21T08:01:00Z)
• Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution [65.91317390645163]
  Upscale-A-Video is a text-guided latent diffusion framework for video upscaling. It ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences. It also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation.
  arXiv  Detail & Related papers  (2023-12-11T18:54:52Z)
• Flow-Guided Diffusion for Video Inpainting [14.168532703086672]
  Video inpainting has been challenged by complex scenarios like large movements and low-light conditions. Current methods, including emerging diffusion models, face limitations in quality and efficiency. This paper introduces the Flow-Guided Diffusion model for Video Inpainting (FGDVI), a novel approach that significantly enhances temporal consistency and inpainting quality.
  arXiv  Detail & Related papers  (2023-11-26T17:48:48Z)
• Diffusion Models as Masked Autoencoders [52.442717717898056]
  We revisit generatively pre-training visual representations in light of recent interest in denoising diffusion models. While directly pre-training with diffusion models does not produce strong representations, we condition diffusion models on masked input and formulate diffusion models as masked autoencoders (DiffMAE) We perform a comprehensive study on the pros and cons of design choices and build connections between diffusion models and masked autoencoders.
  arXiv  Detail & Related papers  (2023-04-06T17:59:56Z)

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.