Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion
Huynh, Lam; Nguyen, Phong; Matas, Jiri; Rahtu, Esa; Heikkilä, Janne (2021)
Huynh, Lam
Nguyen, Phong
Matas, Jiri
Rahtu, Esa
Heikkilä, Janne
IEEE
2021
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202205094498
https://urn.fi/URN:NBN:fi:tuni-202205094498
Kuvaus
Peer reviewed
Tiivistelmä
In this paper, we propose enhancing monocular depth estimation by adding 3D points as depth guidance. Unlike existing depth completion methods, our approach performs well on extremely sparse and unevenly distributed point clouds, which makes it agnostic to the source of the 3D points. We achieve this by introducing a novel multi-scale 3D point fusion network that is both lightweight and efficient. We demonstrate its versatility on two different depth estimation problems where the 3D points have been acquired with conventional structure-from-motion and LiDAR. In both cases, our network performs on par with state-of-the-art depth completion methods and achieves significantly higher accuracy when only a small number of points is used while being more compact in terms of the number of parameters. We show that our method outperforms some contemporary deep learning based multi-view stereo and structure-from-motion methods both in accuracy and in compactness.
Kokoelmat
- TUNICRIS-julkaisut [16977]