ILDiff: Generate Transparent Animated Stickers by Implicit Layout Distillation

• URL: http://arxiv.org/abs/2412.20901v1
• Date: Mon, 30 Dec 2024 12:27:35 GMT
• Title: ILDiff: Generate Transparent Animated Stickers by Implicit Layout Distillation
• Authors: Ting Zhang, Zhiqiang Yuan, Yeshuang Zhu, Jinchao Zhang,
• Abstract summary: High-quality animated stickers usually contain transparent channels, which are often ignored by current video generation models.<n>To generate fine-grained animated transparency channels, existing methods can be roughly divided into video matting algorithms and diffusion-based algorithms.<n>In this paper, we propose an ILDiff method to generate animated transparent channels through implicit layout distillation.
• Score: 17.449524943353904
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-quality animated stickers usually contain transparent channels, which are often ignored by current video generation models. To generate fine-grained animated transparency channels, existing methods can be roughly divided into video matting algorithms and diffusion-based algorithms. The methods based on video matting have poor performance in dealing with semi-open areas in stickers, while diffusion-based methods are often used to model a single image, which will lead to local flicker when modeling animated stickers. In this paper, we firstly propose an ILDiff method to generate animated transparent channels through implicit layout distillation, which solves the problems of semi-open area collapse and no consideration of temporal information in existing methods. Secondly, we create the Transparent Animated Sticker Dataset (TASD), which contains 0.32M high-quality samples with transparent channel, to provide data support for related fields. Extensive experiments demonstrate that ILDiff can produce finer and smoother transparent channels compared to other methods such as Matting Anything and Layer Diffusion. Our code and dataset will be released at link https://xiaoyuan1996.github.io.

Related papers

• OutDreamer: Video Outpainting with a Diffusion Transformer [37.512451098188635]
  We introduce OutDreamer, a DiT-based video outpainting framework.<n>We propose a mask-driven self-attention layer that dynamically integrates the given mask information.<n>For long video outpainting, we employ a cross-video-clip refiner to iteratively generate missing content.
  arXiv  Detail & Related papers  (2025-06-27T15:08:54Z)
• Mobius: Text to Seamless Looping Video Generation via Latent Shift [50.04534295458244]
  We present Mobius, a novel method to generate seamlessly looping videos from text descriptions directly without any user annotations. Our method repurposes the pre-trained video latent diffusion model for generating looping videos from text prompts without any training.
  arXiv  Detail & Related papers  (2025-02-27T17:33:51Z)
• 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)
• UniVST: A Unified Framework for Training-free Localized Video Style Transfer [102.52552893495475]
  This paper presents UniVST, a unified framework for localized video style transfer based on diffusion models. It operates without the need for training, offering a distinct advantage over existing diffusion methods that transfer style across entire videos.
  arXiv  Detail & Related papers  (2024-10-26T05:28:02Z)
• Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models [56.691967706131]
  We view frames as continuous functions in the 2D space, and videos as a sequence of continuous warping transformations between different frames. This perspective allows us to train function space diffusion models only on images and utilize them to solve temporally correlated inverse problems. Our method allows us to deploy state-of-the-art latent diffusion models such as Stable Diffusion XL to solve video inverse problems.
  arXiv  Detail & Related papers  (2024-10-21T16:19:34Z)
• 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)
• COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing [57.76170824395532]
  Video editing is an emerging task, in which most current methods adopt the pre-trained text-to-image (T2I) diffusion model to edit the source video.<n>We propose COrrespondence-guided Video Editing (COVE) to achieve high-quality and consistent video editing.<n>COVE can be seamlessly integrated into the pre-trained T2I diffusion model without the need for extra training or optimization.
  arXiv  Detail & Related papers  (2024-06-13T06:27:13Z)
• Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation [44.92712228326116]
  Video outpainting is a challenging task, aiming at generating video content outside the viewport of the input video. We introduce MOTIA Mastering Video Outpainting Through Input-Specific Adaptation. MoTIA comprises two main phases: input-specific adaptation and pattern-aware outpainting.
  arXiv  Detail & Related papers  (2024-03-20T16:53:45Z)
• Transparent Image Layer Diffusion using Latent Transparency [30.77316047044662]
  We present LayerDiffuse, an approach enabling large-scale pretrained latent diffusion models to generate transparent images. The method learns a "latent transparency" that encodes alpha channel transparency into the latent manifold of a pretrained latent diffusion model. It preserves the production-ready quality of the large diffusion model by regulating the added transparency as a latent offset.
  arXiv  Detail & Related papers  (2024-02-27T01:19:53Z)
• LatentMan: Generating Consistent Animated Characters using Image Diffusion Models [44.18315132571804]
  We propose a zero-shot approach for generating consistent videos of animated characters based on Text-to-Image (T2I) diffusion models. Our proposed approach outperforms existing zero-shot T2V approaches in generating videos of animated characters in terms of pixel-wise consistency and user preference.
  arXiv  Detail & Related papers  (2023-12-12T10:07:37Z)
• MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion [57.90404618420159]
  We introduce Multi-view Ancestral Sampling (MAS), a method for 3D motion generation. MAS works by simultaneously denoising multiple 2D motion sequences representing different views of the same 3D motion. We demonstrate MAS on 2D pose data acquired from videos depicting professional basketball maneuvers.
  arXiv  Detail & Related papers  (2023-10-23T09:05:18Z)
• Hierarchical Masked 3D Diffusion Model for Video Outpainting [20.738731220322176]
  We introduce a masked 3D diffusion model for video outpainting. This allows us to use multiple guide frames to connect the results of multiple video clip inferences. We also introduce a hybrid coarse-to-fine inference pipeline to alleviate the artifact accumulation problem.
  arXiv  Detail & Related papers  (2023-09-05T10:52:21Z)
• Self-Guided Diffusion Models [53.825634944114285]
  We propose a framework for self-guided diffusion models. Our method provides guidance signals at various image granularities. Our experiments on single-label and multi-label image datasets demonstrate that self-labeled guidance always outperforms diffusion models without guidance.
  arXiv  Detail & Related papers  (2022-10-12T17:57:58Z)
• Unsupervised Video Interpolation by Learning Multilayered 2.5D Motion Fields [75.81417944207806]
  This paper presents a self-supervised approach to video frame learning that requires only a single video. We parameterize the video motions by solving an ordinary differentiable equation (ODE) defined on a time-varying motion field. This implicit neural representation learns the video as a space-time continuum, allowing frame-time continuum at any temporal resolution.
  arXiv  Detail & Related papers  (2022-04-21T06:17:05Z)

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.