Abstract
Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision. This is often achieved by employing Structure from Motion (SfM) or Simultaneous Localization and Mapping (SLAM) algorithms based on the real-time requirements. Recently, with the advent of Convolutional Neural Networks (CNNs) researchers have explored the possibility of using machine learning techniques to reconstruct the 3D structure of a scene and jointly predict the camera pose. In this work, we present a framework that achieves state-of-the-art performance on single image depth prediction for both indoor and outdoor scenes. The depth prediction system is then extended to predict optical flow and ultimately the camera pose and trained end-to-end. Our framework outperforms previous deep-learning based motion prediction approaches, and we also demonstrate that the state-of-the-art metric depths can be further improved using the knowledge of pose.
| Original language | English |
|---|---|
| Title of host publication | Computer Vision – ACCV 2018 |
| Subtitle of host publication | 14th Asian Conference on Computer Vision Perth, Australia, December 2–6, 2018 Revised Selected Papers, Part I |
| Editors | C.V. Jawahar, Hongdong Li, Greg Mori, Konrad Schindler |
| Place of Publication | Cham Switzerland |
| Publisher | Springer |
| Pages | 625-642 |
| Number of pages | 18 |
| ISBN (Electronic) | 9783030208875 |
| ISBN (Print) | 9783030208868 |
| DOIs | |
| Publication status | Published - 2019 |
| Event | Asian Conference on Computer Vision 2018 - Perth, Australia Duration: 2 Dec 2018 → 6 Dec 2018 Conference number: 14th https://link-springer-com.ezproxy.lib.monash.edu.au/book/10.1007/978-3-030-20873-8 |
Publication series
| Name | Lecture Notes in Computer Science |
|---|---|
| Publisher | Springer |
| Volume | 11361 |
| ISSN (Print) | 0302-9743 |
| ISSN (Electronic) | 1611-3349 |
Conference
| Conference | Asian Conference on Computer Vision 2018 |
|---|---|
| Abbreviated title | ACCV 2018 |
| Country | Australia |
| City | Perth |
| Period | 2/12/18 → 6/12/18 |
| Internet address |
Keywords
- Depth
- Indoor and outdoor datasets
- Optical flow
- Pose prediction
Cite this
}
ENG : end-to-end neural geometry for robust depth and pose estimation using CNNs. / Dharmasiri, Thanuja; Spek, Andrew; Drummond, Tom.
Computer Vision – ACCV 2018: 14th Asian Conference on Computer Vision Perth, Australia, December 2–6, 2018 Revised Selected Papers, Part I. ed. / C.V. Jawahar; Hongdong Li; Greg Mori; Konrad Schindler. Cham Switzerland : Springer, 2019. p. 625-642 (Lecture Notes in Computer Science; Vol. 11361).Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
TY - GEN
T1 - ENG
T2 - end-to-end neural geometry for robust depth and pose estimation using CNNs
AU - Dharmasiri, Thanuja
AU - Spek, Andrew
AU - Drummond, Tom
PY - 2019
Y1 - 2019
N2 - Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision. This is often achieved by employing Structure from Motion (SfM) or Simultaneous Localization and Mapping (SLAM) algorithms based on the real-time requirements. Recently, with the advent of Convolutional Neural Networks (CNNs) researchers have explored the possibility of using machine learning techniques to reconstruct the 3D structure of a scene and jointly predict the camera pose. In this work, we present a framework that achieves state-of-the-art performance on single image depth prediction for both indoor and outdoor scenes. The depth prediction system is then extended to predict optical flow and ultimately the camera pose and trained end-to-end. Our framework outperforms previous deep-learning based motion prediction approaches, and we also demonstrate that the state-of-the-art metric depths can be further improved using the knowledge of pose.
AB - Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision. This is often achieved by employing Structure from Motion (SfM) or Simultaneous Localization and Mapping (SLAM) algorithms based on the real-time requirements. Recently, with the advent of Convolutional Neural Networks (CNNs) researchers have explored the possibility of using machine learning techniques to reconstruct the 3D structure of a scene and jointly predict the camera pose. In this work, we present a framework that achieves state-of-the-art performance on single image depth prediction for both indoor and outdoor scenes. The depth prediction system is then extended to predict optical flow and ultimately the camera pose and trained end-to-end. Our framework outperforms previous deep-learning based motion prediction approaches, and we also demonstrate that the state-of-the-art metric depths can be further improved using the knowledge of pose.
KW - Depth
KW - Indoor and outdoor datasets
KW - Optical flow
KW - Pose prediction
UR - http://www.scopus.com/inward/record.url?scp=85066778744&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-20887-5_39
DO - 10.1007/978-3-030-20887-5_39
M3 - Conference Paper
AN - SCOPUS:85066778744
SN - 9783030208868
T3 - Lecture Notes in Computer Science
SP - 625
EP - 642
BT - Computer Vision – ACCV 2018
A2 - Jawahar, C.V.
A2 - Li, Hongdong
A2 - Mori, Greg
A2 - Schindler, Konrad
PB - Springer
CY - Cham Switzerland
ER -