Matteo Poggi, Fabio Tosi, Stefano Mattoccia, "Learning monocular depth estimation with unsupervised trinocular assumptions", accepted at 3DV 2018
Abstract
Obtaining accurate depth measurements out of a single image represents a fascinating solution to 3D sensing. CNNs led to great improvements in this field and recent trends replaced the need for ground-truth labels with geometry-guided image reconstruction signals enabling unsupervised training. Currently, for this purpose, state-of-the-art techniques rely on images acquired with a binocular stereo rig to predict inverse depth (i.e., disparity) according to the aforementioned supervision principle. However, these methods suffer from well-known problems near occlusions, left border etc. inherited from the stereo setup.
Therefore, in this paper, we tackle these issues by moving to a trinocular domain for training. Assuming the central image as the reference, we train a CNN to infer disparity representations pairing such image with frames on its left and right side. This allows obtaining depth maps not affected by typical stereo artifacts. Moreover, being trinocular datasets seldom available, we introduce a novel interleaved training procedure enabling to enforce the trinocular assumption outlined from conventional binocular datasets.
Exhaustive experimental results on the KITTI 2015 dataset confirm that our proposal outperforms state-of-the-art methods for unsupervised monocular depth estimation trained on binocular stereo pairs as well as any known methods relying on other cues.
Paper: available soon
Source code and trained model:
[ Ссылка ]
Matteo Poggi: [ Ссылка ]
Fabio Tosi: [ Ссылка ]
Stefano Mattoccia: [ Ссылка ]
We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X GPU used for this research
![](https://i.ytimg.com/vi/uMA5YWJME4M/maxresdefault.jpg)