Monocular depth estimation for glass walls with context: A new dataset and method

• Main Authors: LIANG, Yuan, DENG, Bailin, LIU, Wenxi, QIN, Jing, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Color domains; Depth estimation; Glass detection; Glass walls; Line segment detection; Monocular depth estimation; Rgb colors; Task analysis; Transformer; Transparent glass; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8363; https://ink.library.smu.edu.sg/context/sis_research/article/9366/viewcontent/349366052.pdf
• Institution: Singapore Management University

Traditional monocular depth estimation assumes that all objects are reliably visible in the RGB color domain. However, this is not always the case as more and more buildings are decorated with transparent glass walls. This problem has not been explored due to the difficulties in annotating the depth...