Please use this identifier to cite or link to this item:
http://hdl.handle.net/11375/27011
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | CHEN, JUN | - |
dc.contributor.author | LI, CHENGQI | - |
dc.date.accessioned | 2021-10-07T17:50:03Z | - |
dc.date.available | 2021-10-07T17:50:03Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://hdl.handle.net/11375/27011 | - |
dc.description.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. | en_US |
dc.language.iso | en | en_US |
dc.subject | Natural Image Matting | en_US |
dc.subject | Deep Learning | en_US |
dc.subject | Trimap-Free | en_US |
dc.title | Enabling Trimap-Free Image Matting via Multitask Learning | en_US |
dc.type | Thesis | en_US |
dc.description.degreetype | Thesis | en_US |
dc.description.degree | Master of Science in Electrical and Computer Engineering (MSECE) | en_US |
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.