File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ACCESS.2019.2943885
- Scopus: eid_2-s2.0-85077758631
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Article: Wireframe Parsing with Guidance of Distance Map
Title | Wireframe Parsing with Guidance of Distance Map |
---|---|
Authors | |
Keywords | Artificial neural networks computer vision feature extraction image edge detection |
Issue Date | 2019 |
Citation | IEEE Access, 2019, v. 7, p. 141036-141044 How to Cite? |
Abstract | We propose an end-To-end method for simultaneously detecting local junctions and global wireframe in man-made environment. Our pipeline consists of an anchor-free junction detection module, a distance map learning module, and a line segment proposing and verification module. A set of line segments are proposed from the predicted junctions with guidance of the learned distance map, and further verified by the proposal verification module. Experimental results show that our method outperforms the previous state-of-The-Art wireframe parser by a descent margin. In terms of line segments detection, our method shows competitive performance on standard benchmarks. The proposed networks are end-To-end trainable and efficient.aaThe code will be released on github for reproduction of the results. |
Persistent Identifier | http://hdl.handle.net/10722/345104 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Huang, Kun | - |
dc.contributor.author | Gao, Shenghua | - |
dc.date.accessioned | 2024-08-15T09:25:17Z | - |
dc.date.available | 2024-08-15T09:25:17Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | IEEE Access, 2019, v. 7, p. 141036-141044 | - |
dc.identifier.uri | http://hdl.handle.net/10722/345104 | - |
dc.description.abstract | We propose an end-To-end method for simultaneously detecting local junctions and global wireframe in man-made environment. Our pipeline consists of an anchor-free junction detection module, a distance map learning module, and a line segment proposing and verification module. A set of line segments are proposed from the predicted junctions with guidance of the learned distance map, and further verified by the proposal verification module. Experimental results show that our method outperforms the previous state-of-The-Art wireframe parser by a descent margin. In terms of line segments detection, our method shows competitive performance on standard benchmarks. The proposed networks are end-To-end trainable and efficient.aaThe code will be released on github for reproduction of the results. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Access | - |
dc.subject | Artificial neural networks | - |
dc.subject | computer vision | - |
dc.subject | feature extraction | - |
dc.subject | image edge detection | - |
dc.title | Wireframe Parsing with Guidance of Distance Map | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ACCESS.2019.2943885 | - |
dc.identifier.scopus | eid_2-s2.0-85077758631 | - |
dc.identifier.volume | 7 | - |
dc.identifier.spage | 141036 | - |
dc.identifier.epage | 141044 | - |
dc.identifier.eissn | 2169-3536 | - |