E2LNet: An Efficient and Effective Lightweight Network for Panoramic Depth Estimation
Jiayue Xu, Jianping Zhao, Hua Li, Cheng Han, Chao Xu, Hai Huang, Yuehua Wang, Xuqiang Shao, Ming Meng · 2023
Read E2LNet: An Efficient and Effective Lightweight Network for Panoramic Depth Estimation by Jiayue Xu, Jianping Zhao, Hua Li, Cheng Han, Chao Xu, Hai Huang, Yuehua Wang, Xuqiang Shao, Ming Meng (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10675273.txt.
Description
Jiayue Xu and co-authors present a light network that guesses depth from one panoramic image, in a study from two thousand twenty-three. Wide views help robots and self-driving cars, but warp and wide context strain depth tools. Their design joins a warp-aware attention block with a global scene block.
The attention block flexes its view window by place to handle warp. The scene block folds whole-view context into the feature maps. Tests on three sets, fake and real, matched top rivals on scores. The net is small and bends to new uses with ease. Readers in mobile AR get a depth tool built for tight hardware.
Catalog record
| CREATOR | Jiayue Xu, Jianping Zhao, Hua Li, Cheng Han, Chao Xu, Hai Huang, Yuehua Wang, Xuqiang Shao, Ming Meng |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |