Geometric Pretraining for Monocular Depth Estimation

摘要

ImageNet-pretrained networks have been widely used in transfer learning for monocular depth estimation. These pretrained networks are trained with classification losses for which only semantic information is exploited while spatial information is ignored. However, both semantic and spatial information is important for per-pixel depth estimation. In this paper, we design a novel self-supervised geometric pretraining task that is tailored for monocular depth estimation using uncalibrated videos. The designed task decouples the structure information from input videos by a simple yet effective conditional autoencoder-decoder structure. Using almost unlimited videos from the internet, networks are pretrained to capture a variety of structures of the scene and can be easily transferred to depth estimation tasks using calibrated images. Extensive experiments are used to demonstrate that the proposed geometric-pretrained networks perform better than ImageNet-pretrained networks in terms of accuracy, few-shot learning and generalization ability. Using existing learning methods, geometric-transferred networks achieve new state-of-the-art results by a large margin. The pretrained networks will be open source soon¹ .