paper-with-me

Papers

Adversarially-Guided Portrait Matting

2023-05-04 · Sergej Chicherin, Karen Efremyan

We present a method for generating alpha mattes using a limited data source. We pretrain a novel transformerbased model (StyleMatte) on portrait datasets. We utilize this model to provide image-mask pairs for the StyleGAN3-based network (StyleMatteGAN). This network is trained unsupervisedly and generates previously unseen imagemask training pairs that are fed back to StyleMatte. We demonstrate that the performance of the matte pulling network improves during this cycle and obtains top results on the human portraits and state-of-the-art metrics on animals dataset. Furthermore, StyleMatteGAN provides high-resolution, privacy-preserving portraits with alpha mattes, making it suitable for various image composition tasks. Our code is available at https://github.com/chroneus/stylematte

📄 PDF Abstract BibTeX arXiv:2305.02981

Code (1)

chroneus/stylematte 공식 구현 pytorch

Tasks

Image MattingPrivacy Preserving

Similar Papers 제목 키워드 기반

Fast Deep Matting for Portrait Animation on Mobile Phone

2017-07-26 · Bingke Zhu, Yingying Chen, Jinqiao Wang, Si Liu 외

Image matting plays an important role in image and video editing. However, the formulation of image matting is inherently ill-posed. Traditional methods usually employ interaction to deal with the image matting problem w…

Image MattingPortrait AnimationVideo Editing

Efficient Portrait Matte Creation With Layer Diffusion and Connectivity Priors

2025-01-27 · Zhiyuan Lu, Hao Lu, Hua Huang

Learning effective deep portrait matting models requires training data of both high quality and large quantity. Neither quality nor quantity can be easily met for portrait matting, however. Since the most accurate ground…

Image MattingVideo SegmentationVideo Semantic Segmentation

Self-supervised Matting-specific Portrait Enhancement and Generation

2022-08-13 · Yangyang Xu Zeyang Zhou, Shengfeng He

We resolve the ill-posed alpha matting problem from a completely different perspective. Given an input portrait image, instead of estimating the corresponding alpha matte, we focus on the other end, to subtly enhance thi…

Image MattingSpecificity

Privacy-Preserving Portrait Matting

2021-04-29 · Jizhizi Li, Sihan Ma, Jing Zhang, DaCheng Tao

Recently, there has been an increasing concern about the privacy issue raised by using personally identifiable information in machine learning. However, previous portrait matting methods were all based on identifiable po…

Image MattingPrivacy Preserving

MODNet-V: Improving Portrait Video Matting via Background Restoration

2021-09-24 · Jiayu Sun, Zhanghan Ke, Lihe Zhang, Huchuan Lu 외

To address the challenging portrait video matting problem more precisely, existing works typically apply some matting priors that require additional user efforts to obtain, such as annotated trimaps or background images.…

GPUImage MattingVideo Matting