Monodepth

Assignment №5 from course "Deep Vision and Graphics" taught at YSDA (https://github.com/yandexdataschool/deep_vision_and_graphics) Original paper: https://arxiv.org/pdf/1609.03677.pdf Method exploit epipolar geometry to generate disparity images by training our network with an image reconstruction loss. Training loss enforces consistency between the disparities produced relative to both the left and right images, leading to improved performance and robustness compared to existing approaches.