사이트맵

European Conference on Computer Vision

ECCV 2018: Computer Vision 

『Learning-Based Video Motion Magnification』

Authors

Tae-Hyun Oh, Ronnachai Jaroensri, Changil Kim, Mohamed Elgharib, Frédo Durand, William T. Freeman & Wojciech Matusik 

Abstract

Video motion magnification techniques allow us to see small motions previously invisible to the naked eyes, such as those of vibrating airplane wings, or swaying buildings under the influence of the wind. Because the motion is small, the magnification results are prone to noise or excessive blurring. The state of the art relies on hand-designed filters to extract representations that may not be optimal. In this paper, we seek to learn the filters directly from examples using deep convolutional neural networks. To make training tractable, we carefully design a synthetic dataset that captures small motion well, and use two-frame input for training. We show that the learned filters achieve high-quality results on real videos, with less ringing artifacts and better noise characteristics than previous methods. While our model is not trained with temporal filters, we found that the temporal filters can be used with our extracted representations up to a moderate magnification, enabling a frequency-based motion selection. Finally, we analyze the learned filters and show that they behave similarly to the derivative filters used in previous works. Our code, trained model, and datasets will be available online. 

Review

사람 눈에 보이지 않을 만큼 작은 비디오 내의 움직임을 고화질을 유지하며 눈에 띄게 크게 증폭시키는 인공신경망을 제안한 연구

본 방법론을 통해, 사람의 두상 영상 비디오만으로 심장박동을 비접촉 방식으로 측정할 수 있으며, 엔진 등의 기계 진동 분석, 건축 구조물의 공진 주파수 분석 등에 응용

ECCV'2018 구두 발표 논문 (Oral paper, 2%의 acceptance rate) 선정

(관련 영상: https://youtu.be/GrMLeEcSNzY)