Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Seokju | - |
dc.contributor.author | Im, Sunghoon | - |
dc.contributor.author | Lin, Stephen | - |
dc.contributor.author | Kweon, In So | - |
dc.date.accessioned | 2023-12-26T19:12:18Z | - |
dc.date.available | 2023-12-26T19:12:18Z | - |
dc.date.created | 2021-06-04 | - |
dc.date.issued | 2021-02-05 | - |
dc.identifier.isbn | 9781577358664 | - |
dc.identifier.issn | 2374-3468 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/46946 | - |
dc.description.abstract | We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion, and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we highlight the fundamental difference between inverse and forward projection while modeling the individual motion of each rigid object, and propose a geometrically correct projection pipeline using a neural forward projection module. Second, we design a unified instance-aware photometric and geometric consistency loss that holistically imposes self-supervisory signals for every background and object region. Lastly, we introduce a general-purpose auto-annotation scheme using any off-the-shelf instance segmentation and optical flow models to produce video instance segmentation maps that will be utilized as input to our training pipeline. These proposed elements are validated in a detailed ablation study. Through extensive experiments conducted on the KITTI and Cityscapes dataset, our framework is shown to outperform the state-of-the-art depth and motion estimation methods. Our code, dataset, and models are publicly available. | - |
dc.language | English | - |
dc.publisher | Association for the Advancement of Artificial Intelligence(AAAI) | - |
dc.title | Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency | - |
dc.type | Conference Paper | - |
dc.identifier.doi | 10.1609/aaai.v35i3.16281 | - |
dc.identifier.scopusid | 2-s2.0-85130038874 | - |
dc.identifier.bibliographicCitation | AAAI Conference on Artificial Intelligence, pp.1863 - 1872 | - |
dc.identifier.url | https://ojs.aaai.org/index.php/AAAI/article/view/16281 | - |
dc.citation.conferencePlace | US | - |
dc.citation.conferencePlace | Virtual | - |
dc.citation.endPage | 1872 | - |
dc.citation.startPage | 1863 | - |
dc.citation.title | AAAI Conference on Artificial Intelligence | - |
There are no files associated with this item.