Title | ||
---|---|---|
SelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environments |
Abstract | ||
---|---|---|
We present a novel algorithm for self-supervised monocular depth completion. Our approach is based on training a neural network that requires only sparse depth measurements and corresponding monocular video sequences without dense depth labels. Our self-supervised algorithm is designed for challenging indoor environments with textureless regions, glossy and transparent surfaces, moving people, longer and diverse depth ranges and scenes captured by complex ego-motions. Our novel architecture leverages both deep stacks of sparse convolution blocks to extract sparse depth features and pixel-adaptive convolutions to fuse image and depth features. We compare with existing approaches in NYUv2, KITTI and NAVERLABS indoor datasets, and observe 5 - 34 % improvements in root-means-square error (RMSE) reduction. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICRA48506.2021.9560831 | 2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) |
DocType | Volume | Issue |
Conference | 2021 | 1 |
ISSN | Citations | PageRank |
1050-4729 | 0 | 0.34 |
References | Authors | |
24 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jaehoon Choi | 1 | 37 | 15.99 |
Dongki Jung | 2 | 0 | 1.01 |
Yonghan Lee | 3 | 3 | 2.88 |
Deokhwa Kim | 4 | 0 | 1.35 |
Dinesh Manocha | 5 | 9551 | 787.40 |
Donghwan Lee | 6 | 25 | 9.30 |