A Deep Learning Method for Frame Selection in Videos for Structure from Motion Pipelines
METADATA ONLY
Loading...
Author / Producer
Date
2021
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
Structure-from-Motion (SfM) using the frames of a video sequence can be a challenging task because there is a lot of redundant information, the computational time increases quadratically with the number of frames, there would be low-quality images (e.g., blurred frames) that can decrease the final quality of the reconstruction, etc. To overcome all these issues, we present a novel deep-learning architecture that is meant for speeding up SfM by selecting frames using predicted sub-sampling frequency. This architecture is general and can learn/distill the knowledge of any algorithm for selecting frames from a video for generating high-quality reconstructions. One key advantage is that we can run our architecture in real-time saving computations while keeping high-quality results.
Permanent link
Publication status
published
Editor
Book title
2021 IEEE International Conference on Image Processing (ICIP)
Journal / series
Volume
Pages / Article No.
3667 - 3671
Publisher
IEEE
Event
28th IEEE International Conference on Image Processing (ICIP 2021)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Structure from Motion; Deep Learning; Point-Cloud Generation; Video Processing
Organisational unit
Notes
Funding
- ENergy aware BIM Cloud Platform in a COst-effective Building REnovation Context ()