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

• Main Authors: Zheng, Chuanxia, Cham, Tat-Jen, Cai, Jianfei
• 其他作者: School of Computer Science and Engineering
• 格式: Conference or Workshop Item
• 語言: English
• 出版: 2020
• 主題: Engineering::Computer science and engineering; Single-image Depth Estimation; Unpaired Images
• 在線閱讀: https://hdl.handle.net/10356/138497
• 機構: 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...