Publications
Detailed Information
CostDCNet: Cost Volume Based Depth Completion for a Single RGB-D Image
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kam, Jaewon | - |
dc.contributor.author | Kim, Jungeon | - |
dc.contributor.author | Kim, Soongjin | - |
dc.contributor.author | Park, Jaesik | - |
dc.contributor.author | Lee, Seungyong | - |
dc.date.accessioned | 2024-05-09T04:12:16Z | - |
dc.date.available | 2024-05-09T04:12:16Z | - |
dc.date.created | 2024-05-08 | - |
dc.date.created | 2024-05-08 | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Lecture Notes in Computer Science, Vol.13662, pp.257-274 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | https://hdl.handle.net/10371/201288 | - |
dc.description.abstract | Successful depth completion from a single RGB-D image requires both extracting plentiful 2D and 3D features and merging these heterogeneous features appropriately. We propose a novel depth completion framework, CostDCNet, based on the cost volume-based depth estimation approach that has been successfully employed for multi-view stereo (MVS). The key to high-quality depth map estimation in the approach is constructing an accurate cost volume. To produce a quality cost volume tailored to single-view depth completion, we present a simple but effective architecture that can fully exploit the 3D information, three options to make an RGB-D feature volume, and per-plane pixel shuffle for efficient volume upsampling. Our CostDCNet framework consists of lightweight deep neural networks (∼ 1.8M parameters), running in real time (∼ 30 ms). Nevertheless, thanks to our simple but effective design, CostDCNet demonstrates depth completion results comparable to or better than the state-of-the-art methods. | - |
dc.language | 영어 | - |
dc.publisher | Springer Verlag | - |
dc.title | CostDCNet: Cost Volume Based Depth Completion for a Single RGB-D Image | - |
dc.type | Article | - |
dc.identifier.doi | 10.1007/978-3-031-20086-1_15 | - |
dc.citation.journaltitle | Lecture Notes in Computer Science | - |
dc.identifier.wosid | 000899248700015 | - |
dc.identifier.scopusid | 2-s2.0-85142766772 | - |
dc.citation.endpage | 274 | - |
dc.citation.startpage | 257 | - |
dc.citation.volume | 13662 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Park, Jaesik | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.subject.keywordAuthor | Depth completion | - |
dc.subject.keywordAuthor | Cost volume | - |
dc.subject.keywordAuthor | 3D convolution | - |
dc.subject.keywordAuthor | Single RGB-D image | - |
- 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.