Adversarial Learning for Joint Optimization of Depth and Ego-Motion
IEEE Trans. Image Processing, pp. 4130-4142, 2020.
In recent years, supervised deep learning methods have shown a great promise in dense depth estimation. However, massive high-quality training data are expensive and impractical to acquire. Alternatively, self-supervised learning-based depth estimators can learn the latent transformation from monocular or binocular video sequences by mini...More
Full Text (Upload PDF)
PPT (Upload PPT)