File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICCV.2019.00771
- Scopus: eid_2-s2.0-85081931994
- WOS: WOS:000548549202071
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery
Title | Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery |
---|---|
Authors | |
Issue Date | 2020 |
Publisher | IEEE. |
Citation | IEEE International Conference on Computer Vision (ICCV 2019), Seoul, Korea, 27 October - 2 November 2019. In Conference Proceedings, 2020, p. 7617-7626 How to Cite? |
Abstract | In this paper, we propose a novel iterative multi-task framework to complete the segmentation mask of an occluded vehicle and recover the appearance of its invisible parts. In particular, firstly, to improve the quality of the segmentation completion, we present two coupled discriminators that introduce an auxiliary 3D model pool for sampling authentic silhouettes as adversarial samples. In addition, we propose a two-path structure with a shared network to enhance the appearance recovery capability. By iteratively performing the segmentation completion and the appearance recovery, the results will be progressively refined. To evaluate our method, we present a dataset, Occluded Vehicle dataset, containing synthetic and real-world occluded vehicle images. Based on this dataset, we conduct comparison experiments and demonstrate that our model outperforms the state-of-the-arts in both tasks of recovering segmentation mask and appearance for occluded vehicles. Moreover, we also demonstrate that our appearance recovery approach can benefit the occluded vehicle tracking in real-world videos. |
Persistent Identifier | http://hdl.handle.net/10722/273023 |
ISBN | |
ISSN | |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yan, X | - |
dc.contributor.author | Yu, Y | - |
dc.contributor.author | Wang, F | - |
dc.contributor.author | Liu, W | - |
dc.contributor.author | He, S | - |
dc.contributor.author | Pan, J | - |
dc.date.accessioned | 2019-08-06T09:21:05Z | - |
dc.date.available | 2019-08-06T09:21:05Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | IEEE International Conference on Computer Vision (ICCV 2019), Seoul, Korea, 27 October - 2 November 2019. In Conference Proceedings, 2020, p. 7617-7626 | - |
dc.identifier.isbn | 9781728148038 | - |
dc.identifier.issn | 2380-7504 | - |
dc.identifier.uri | http://hdl.handle.net/10722/273023 | - |
dc.description.abstract | In this paper, we propose a novel iterative multi-task framework to complete the segmentation mask of an occluded vehicle and recover the appearance of its invisible parts. In particular, firstly, to improve the quality of the segmentation completion, we present two coupled discriminators that introduce an auxiliary 3D model pool for sampling authentic silhouettes as adversarial samples. In addition, we propose a two-path structure with a shared network to enhance the appearance recovery capability. By iteratively performing the segmentation completion and the appearance recovery, the results will be progressively refined. To evaluate our method, we present a dataset, Occluded Vehicle dataset, containing synthetic and real-world occluded vehicle images. Based on this dataset, we conduct comparison experiments and demonstrate that our model outperforms the state-of-the-arts in both tasks of recovering segmentation mask and appearance for occluded vehicles. Moreover, we also demonstrate that our appearance recovery approach can benefit the occluded vehicle tracking in real-world videos. | - |
dc.language | eng | - |
dc.publisher | IEEE. | - |
dc.relation.ispartof | 2019 IEEE/CVF International Conference on Computer Vision (ICCV) | - |
dc.title | Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Pan, J: jpan@cs.hku.hk | - |
dc.identifier.authority | Pan, J=rp01984 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICCV.2019.00771 | - |
dc.identifier.scopus | eid_2-s2.0-85081931994 | - |
dc.identifier.hkuros | 300346 | - |
dc.identifier.spage | 7617 | - |
dc.identifier.epage | 7626 | - |
dc.identifier.isi | WOS:000548549202071 | - |
dc.publisher.place | United States | - |