Please use this identifier to cite or link to this item:
http://hdl.handle.net/11375/27011
Title: | Enabling Trimap-Free Image Matting via Multitask Learning |
Authors: | LI, CHENGQI |
Advisor: | CHEN, JUN |
Keywords: | Natural Image Matting;Deep Learning;Trimap-Free |
Publication Date: | 2021 |
Abstract: | Trimap-free natural image matting problem is an important computer vision task in which we extract foreground objects from given images without extra trimap input. Compared with trimap-based matting algorithms, trimap-free algorithms are easier to make false detection when the foreground object is not well defined. To solve the problem, we design a novel structure (SegMatting) to handle foreground segmentation and alpha matte prediction simultaneously, which is able to produce high-quality mattes based on RGB inputs alone. This entangled structure enables information exchange between the binary segmentation task and the alpha matte prediction task interactively, and we further design a hybrid loss to adaptively balance two tasks during the multitask learning process. Additionally, we adopt a salient object detection dataset to pretrain our network so that we could obtain a more accurate foreground segment before our training process. Experiments indicate that the proposed SegMatting qualitatively and quantitatively outperforms most previous trimap-free models with a significant margin, while remains competitive among trimap-based methods. |
URI: | http://hdl.handle.net/11375/27011 |
Appears in Collections: | Open Access Dissertations and Theses |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Li_Chengqi_202108_MSECE.pdf | 68.19 MB | Adobe PDF | View/Open |
Items in MacSphere are protected by copyright, with all rights reserved, unless otherwise indicated.