T2Net : synthetic-to-realistic translation for solving single-image depth estimation tasks

• Main Authors: Zheng, Chuanxia, Cham, Tat-Jen, Cai, Jianfei
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2020
• Subjects: Engineering::Computer science and engineering; Single-image Depth Estimation; Unpaired Images
• Online Access: https://hdl.handle.net/10356/138497
• Institution: Nanyang Technological University

Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images, that comprises an image translation network for enhancing reali...