The 9th International Conference on Next Generation Computing 2023 (2023.12)바로가기
페이지
pp.55-56
저자
Yun-Young Chang, Joo-Hee Oh, Abrar Alabdulwahab, Chan-Young Choi, Sang-Woong Lee
언어
영어(ENG)
URL
https://www.earticle.net/Article/A448116
원문정보
초록
영어
Global-Local Path Network is a monocular depth estimation network. It presents a new method for integrating global features from an encoder and local features from a decoder through a Selective Feature Fusion module. In this paper, we propose that replacing the SegFormer encoder with the Swin Transformer leads to an improved GLPN, called Swin Transformer-Global-Local-Path-Network. We train the network with modified NYU Depth V2 datasets. Therefore, with the 0.034 RMSE, 0.075 AbsRel, 0.033 log10, 0.951 Delta 1, 0.994 Delta 2, 0.999 Delta 3, our network using a tiny version of Swin Transformer outperforms the previous GLPN model.
목차
Abstract I. INTRODUCTION II. RELATED WORKS A. Monocular Depth Estimation B. GLPN C. SegFormer D. Swin Transformer III. METHODS A. Overall Architecture B. Light and Strong Encoder IV. EXPERIMENTS A. Datasets B. Settings C. Results V. CONCLUSION ACKNOWLEDGMENT REFERENCES
키워드
GLPNSwin Transformermonocular depth estimation
저자
Yun-Young Chang [ School of Computing Gachon University ]
Joo-Hee Oh [ School of Computing Gachon University ]
Abrar Alabdulwahab [ School of Computing Gachon University ]
Chan-Young Choi [ School of Computing Gachon University ]
Sang-Woong Lee [ School of Computing Gachon University ]
Corresponding Author