Improving Depth Estimation by Embedding Semantic Segmentation: A Hybrid CNN Model

Single image depth estimation works fail to separate foreground elements because they can easily be confounded with the background. To alleviate this problem, we propose the use of a semantic segmentation procedure that adds information to a depth estimator, in this case, a 3D Convolutional Neural Network (CNN)—segmentation is coded as one-hot planes representing categories of objects. We explore 2D and 3D models. Particularly, we propose a hybrid 2D–3D CNN architecture capable of obtaining semantic segmentation and depth estimation at the same time. We tested our procedure on the SYNTHIA-AL dataset and obtained σ₃ = 0.95, which is an improvement of 0.14 points (compared with the state of the art of σ₃ = 0.81) by using manual segmentation, and σ₃ = 0.89 using automatic semantic segmentation, proving that depth estimation is improved when the shape and position of objects in a scene are known.