Matting by Generation
Zhixiang Wang, Baiang Li, Jian Wang, Yu-Lun Liu, Jinwei Gu, Yung-Yu, Chuang, Shin'ichi Satoh

TL;DR
This paper presents a novel image matting approach using generative diffusion models, achieving high-resolution, detailed, and photorealistic mattes with versatility in guidance methods.
Contribution
It introduces a generative modeling framework for image matting leveraging latent diffusion models, with architectural innovations and extensive evaluations demonstrating superior performance.
Findings
Outperforms existing methods on benchmark datasets
Produces high-resolution, detailed, and photorealistic mattes
Works effectively with guidance-free and guidance-based approaches
Abstract
This paper introduces an innovative approach for image matting that redefines the traditional regression-based task as a generative modeling challenge. Our method harnesses the capabilities of latent diffusion models, enriched with extensive pre-trained knowledge, to regularize the matting process. We present novel architectural innovations that empower our model to produce mattes with superior resolution and detail. The proposed method is versatile and can perform both guidance-free and guidance-based image matting, accommodating a variety of additional cues. Our comprehensive evaluation across three benchmark datasets demonstrates the superior performance of our approach, both quantitatively and qualitatively. The results not only reflect our method's robust effectiveness but also highlight its ability to generate visually compelling mattes that approach photorealistic quality. The…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsDiffusion
