Depth Estimation Using Adaptive Bins via Global Attention at High Resolution
Type
ThesisAuthors
Bhat, Shariq
Advisors
Wonka, Peter
Committee members
Hadwiger, Markus
Ghanem, Bernard

Program
Computer ScienceDate
2021-04-21Permanent link to this record
http://hdl.handle.net/10754/668894
Metadata
Show full item recordAbstract
We address the problem of estimating a high quality dense depth map from a single RGB input image. We start out with a baseline encoder-decoder convolutional neural network architecture and pose the question of how the global processing of information can help improve overall depth estimation. To this end, we propose a transformer-based architecture block that divides the depth range into bins whose center value is estimated adaptively per image. The final depth values are estimated as linear combinations of the bin centers. We call our new building block AdaBins. Our results show a decisive improvement over the state-of-the-art on several popular depth datasets across all metrics. We also validate the effectiveness of the proposed block with an ablation study.Citation
Bhat, S. (2021). Depth Estimation Using Adaptive Bins via Global Attention at High Resolution. KAUST Research Repository. https://doi.org/10.25781/KAUST-AC1MYae974a485f413a2113503eed53cd6c53
10.25781/KAUST-AC1MY