Name
Title | ||
|---|---|---|
On Reproducing Semi-dense Depth Map Reconstruction using Deep Convolutional Neural Networks with Perceptual Loss |
Abstract | ||
|---|---|---|
In our recent papers, we proposed a new family of residual convolutional neural networks trained for semi-dense and sparse depth reconstruction without use of RGB channel. The proposed models can be used in low-resolution depth sensors or SLAM methods estimating partial depth with certain distributions. We proposed using perceptual loss for training depth reconstruction in order to better preserve edge structure and reduce over-smoothness of models trained on MSE loss alone. This paper contains reproducibility companion guide on training, running and evaluating suggested methods, while also presenting links on further studies in view of reviewers comments and related problems of depth reconstruction.
|
Year | DOI | Venue |
|---|---|---|
2019 | 10.1145/3343031.3351167 | Proceedings of the 27th ACM International Conference on Multimedia |
Keywords | Field | DocType |
augmented reality, autonomous vehicles, computer vision, convolutional neural networks, depth map, mixed reality | Computer vision,Convolutional neural network,Computer science,Artificial intelligence,Depth map,Perception | Conference |
ISBN | Citations | PageRank |
978-1-4503-6889-6 | 0 | 0.34 |
References | Authors | |
0 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ilya Makarov | 1 | 12 | 14.21 |
| Dmitrii Maslov | 2 | 0 | 0.34 |
| Olga Gerasimova | 3 | 8 | 6.89 |
| Vladimir Aliev | 4 | 3 | 2.76 |
| Alisa Korinevskaya | 5 | 0 | 2.03 |
| Ujjwal Sharma | 6 | 0 | 0.68 |
| Haoliang Wang | 7 | 1 | 3.39 |