Improving three-dimensional reconstruction of buildings from web-harvested images using forensic clues

Milani, Simone; Tronca, Enrico

doi:10.1117/1.jei.26.1.011009

Cited by 2 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some other works [3,5,6] pay more attention to optimizing the camera motion and the structure estimation at the same time, by exploiting the connection between the motion and structure. The traditional SfM methods have already made great progress in the past decades and proven the effectiveness for the real applications on different tasks such as the scene reconstruction [5,7,8,9,10], and the 3D object modeling [11]. However, there still exist problems that need to be further solved such as time efficiency.…”

Section: Related Workmentioning

confidence: 99%

A Deep Learning Method for Frame Selection in Videos for Structure from Motion Pipelines

Banterle

Gong

Corsini

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

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.

show abstract