Bi-projection-based Foreground-aware Omnidirectional Depth Prediction

Feng, Qi; Shum, Hubert P.H.; Morishima, Shigeo

Abstract

Due to the increasing availability of commercial 360- degree cameras, accurate depth prediction for omnidirectional images can be beneficial to a wide range of applications including video editing and augmented reality. Regarding existing methods, some focus on learning high-quality global prediction while fail to capture detailed local features. Others suggest integrating local context into the learning procedure, they yet propose to train on non-foreground-aware databases. In this paper, we explore to simultaneously use equirectangular and cube-map projection to learn omnidirectional depth prediction from foreground-aware databases in a multi-task manner. Experimental results demonstrate improved performance when compared to the state-of-the-art.

Citation

Feng, Q., Shum, H. P., & Morishima, S. (2023, September). Bi-projection-based Foreground-aware Omnidirectional Depth Prediction. Presented at Visual Computing 2021, Online

• Presentation Conference Type: Conference Paper (published)
• Conference Name: Visual Computing 2021
• Start Date: Sep 28, 2023
• End Date: Oct 1, 2021
• Acceptance Date: Aug 1, 2021
• Publication Date: 2021
• Deposit Date: Aug 13, 2021
• Public URL: https://durham-repository.worktribe.com/output/1138596
• Publisher URL: https://cgvi.jp/vc2021/program/oral/