ILDiff: Generate Transparent Animated Stickers by Implicit Layout Distillation

TL;DR

ILDiff is a novel method that generates high-quality, transparent animated stickers by implicitly distilling layout information, effectively addressing semi-open area issues and temporal consistency, supported by a new large-scale dataset.

Contribution

The paper introduces ILDiff, a new approach for animated transparent channel generation using implicit layout distillation, and provides a large-scale dataset TASD for training and evaluation.

Findings

ILDiff produces finer, smoother transparent channels than existing methods.

The TASD dataset contains 0.32 million high-quality samples for research.

Extensive experiments validate ILDiff's superior performance.

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.