DA-NET : Monocular Depth Estimation using Disparity maps Awareness NETwork

Antoine Billy (1, 2) , Pascal Desbarats (2)

1 I2S
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique

Estimating depth from 2D images has become an active field of study in autonomous driving, scene reconstruction , 3D object recognition, segmentation, and detection. Best performing methods are based on Convolutional Neural Networks, and, as the process of building an appropriate set of data requires a tremendous amount of work, almost all of them rely on the same benchmark to compete between each other : The KITTI benchmark. However, most of them will use the ground truth generated by the LiDAR sensor which generates very sparse depth map with sometimes less than 5% of the image density, ignoring the second image that is given for stereo estimation. Recent approaches have shown that the use of both input images given in most of the depth estimation data set significantly improve the generated results. This paper is in line with this idea, we developed a very simple yet efficient model based on the U-NET architecture that uses both stereo images in the training process. We demonstrate the effectiveness of our approach and show high quality results comparable to state-of-the-art methods on the KITTI benchmark.

Mots clés: Monocular Depth Estimation; Disparity Images; Stereo Vision; Convolutional Networks; U-NET

Domaines: Traitement des images [eess.IV]

Antoine Billy, Pascal Desbarats. DA-NET : Monocular Depth Estimation using Disparity maps Awareness NETwork. International Conference on Computer Vision Theory and Applications (VISAPP), 2020. ⟨hal-02508853⟩