Publications
Detailed Information
Stad: Stable Video Depth Estimation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Hyunmin | - |
dc.contributor.author | Park, Jaesik | - |
dc.date.accessioned | 2024-05-09T04:13:01Z | - |
dc.date.available | 2024-05-09T04:13:01Z | - |
dc.date.created | 2024-05-08 | - |
dc.date.created | 2024-05-08 | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Proceedings - International Conference on Image Processing, ICIP, Vol.2021-September, pp.3213-3217 | - |
dc.identifier.issn | 1522-4880 | - |
dc.identifier.uri | https://hdl.handle.net/10371/201302 | - |
dc.description.abstract | We present a method for estimating temporally stable depth video from a sequence of images. We extend the prior work aimed at video depth estimation, Neural-RGBD [1], which proposed to use temporal information by accumulating a depth probability volume over time. We propose three simple yet effective ideas to gain improvement: (1) temporal attention module to select and propagate only the meaningful temporal information, (2) geometric warping operation to warp neighbor features in the way of preserving geometry cues, and (3) scale-invariant loss to relieve the inherent scale ambiguity problem in monocular depth estimation task. We demonstrate the efficiency of proposed ideas by comparing our proposed network STAD with the state-of-the-arts. Moreover, we compare STAD with its per-frame network STAD-frame to show the importance of utilizing temporal information. The experimental results show that STAD significantly improved the baseline accuracy without a large parameter increase. | - |
dc.language | 영어 | - |
dc.publisher | ICIP | - |
dc.title | Stad: Stable Video Depth Estimation | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ICIP42928.2021.9506521 | - |
dc.citation.journaltitle | Proceedings - International Conference on Image Processing, ICIP | - |
dc.identifier.wosid | 000819455103067 | - |
dc.identifier.scopusid | 2-s2.0-85125593146 | - |
dc.citation.endpage | 3217 | - |
dc.citation.startpage | 3213 | - |
dc.citation.volume | 2021-September | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Park, Jaesik | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.subject.keywordAuthor | Computer Vision | - |
dc.subject.keywordAuthor | Depth Estimation | - |
dc.subject.keywordAuthor | Video Depth Estimation | - |
dc.subject.keywordAuthor | Temporal Attention | - |
dc.subject.keywordAuthor | 3D Geometry | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.