DC Field | Value | Language |
---|---|---|
dc.contributor.author | Bangunharcana, Antyanta | ko |
dc.contributor.author | Kim, Soohyun | ko |
dc.contributor.author | Kim, Kyung-Soo | ko |
dc.date.accessioned | 2023-09-19T09:04:17Z | - |
dc.date.available | 2023-09-19T09:04:17Z | - |
dc.date.created | 2023-09-19 | - |
dc.date.issued | 2022-06 | - |
dc.identifier.citation | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022, pp.1905 - 1915 | - |
dc.identifier.issn | 2160-7508 | - |
dc.identifier.uri | http://hdl.handle.net/10203/312765 | - |
dc.description.abstract | This work focuses on improving the Conv-GRU-based optical flow update within a DROID-SLAM framework. Prior optical flow models typically follow a UNet or coarse-to-fine architecture in order to extract long-range cross-correlation and context cues. This helps flow estimation in the presence of large motion and challenging image regions, e.g., textureless regions. We propose modifications to the Conv-GRU module which follows the rationale of these prior models by integrating (Atrous) Spatial Pyramid Pooling and global self-attention into the Conv-GRU block. By enlarging the receptive field through the aforementioned modifications, the model is able to integrate information from a larger context window, thus improving the robustness even when given inputs that comprise challenging image regions. We show empirically through extensive experiments the gain in accuracy through these modifications. | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society | - |
dc.title | Revisiting the Receptive Field of Conv-GRU in DROID-SLAM | - |
dc.type | Conference | - |
dc.identifier.wosid | 000861612701102 | - |
dc.identifier.scopusid | 2-s2.0-85137776824 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 1905 | - |
dc.citation.endingpage | 1915 | - |
dc.citation.publicationname | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | New Orleans, LA | - |
dc.identifier.doi | 10.1109/CVPRW56347.2022.00207 | - |
dc.contributor.localauthor | Kim, Soohyun | - |
dc.contributor.localauthor | Kim, Kyung-Soo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.