Paper Info
Title
Learning 3d Human Dynamics From Video
Abstract
From an image of a person in action, we can easily guess the 3D motion of the person in the immediate past and future. This is because we have a mental model of 3D human dynamics that we have acquired from observing visual sequences of humans in motion. We present a framework that can similarly learn a representation of 3D dynamics of humans from video via a simple but effective temporal encoding of image features. At test time, from video, the learned temporal representation give rise to smooth 3D mesh predictions. From a single image, our model can recover the current 3D mesh as well as its 3D past and future motion. Our approach is designed so it can learn from videos with 2D pose annotations in a semi-supervised manner. Though annotated data is always limited, there are millions of videos uploaded daily on the Internet. In this work, we harvest this Internet-scale source of unlabeled data by training our model on unlabeled video with pseudo-ground truth 2D pose obtained from an off-the-shelf 2D pose detector. Our experiments show that adding more videos with pseudo-ground truth 2D pose monotonically improves 3D prediction performance. We evaluate our model on the recent challenging dataset of 3D Poses in the Wild and obtain state-of-the-art performance on the 3D prediction task without any fine-tuning.
Year
DOI
Venue
2018
10.1109/CVPR.2019.00576
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
Field
DocType
Volume
Computer vision,Mental model,Polygon mesh,Pattern recognition,Feature (computer vision),Computer science,Upload,Human dynamics,Artificial intelligence,Detector,The Internet,Encoding (memory)
Journal
abs/1812.01601
ISSN
Citations 
PageRank 
1063-6919
18
0.54
References 
Authors
29
4
Name
Order
Citations
PageRank
Angjoo Kanazawa127210.36
Zhang Jason Y.2237.31
Panna Felsen31063.99
Jitendra Malik4394453782.10