Matting by Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910547156402176 |
|---|---|
| author | Wang, Zhixiang Li, Baiang Wang, Jian Liu, Yu-Lun Gu, Jinwei Chuang, Yung-Yu Satoh, Shin'ichi |
| author_facet | Wang, Zhixiang Li, Baiang Wang, Jian Liu, Yu-Lun Gu, Jinwei Chuang, Yung-Yu Satoh, Shin'ichi |
| contents | 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 project page for this paper is available at https://lightchaserx.github.io/matting-by-generation/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_21017 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Matting by Generation Wang, Zhixiang Li, Baiang Wang, Jian Liu, Yu-Lun Gu, Jinwei Chuang, Yung-Yu Satoh, Shin'ichi Computer Vision and Pattern Recognition 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 project page for this paper is available at https://lightchaserx.github.io/matting-by-generation/ |
| title | Matting by Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.21017 |