Imperial College London
Portrait Picture

DR BERNHARD KAINZ

Faculty of Engineering, Department of Computing

Reader in Medical Image Computing
 
 
 
//

Contact

 

+44 (0)20 7594 8349b.kainz Website CV

 
 
//

Location

 

372Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Schmidtke:2023:10.1007/978-3-031-25066-8_42,
author = {Schmidtke, L and Hou, B and Vlontzos, A and Kainz, B},
doi = {10.1007/978-3-031-25066-8_42},
pages = {704--713},
title = {Self-supervised 3D Human Pose Estimation in Static Video via Neural Rendering},
url = {http://dx.doi.org/10.1007/978-3-031-25066-8_42},
year = {2023}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Inferring 3D human pose from 2D images is a challenging and long-standing problem in the field of computer vision with many applications including motion capture, virtual reality, surveillance or gait analysis for sports and medicine. We present preliminary results for a method to estimate 3D pose from 2D video containing a single person and a static background without the need for any manual landmark annotations. We achieve this by formulating a simple yet effective self-supervision task: our model is required to reconstruct a random frame of a video given a frame from another timepoint and a rendered image of a transformed human shape template. Crucially for optimisation, our ray casting based rendering pipeline is fully differentiable, enabling end to end training solely based on the reconstruction task.
AU  - Schmidtke,L
AU  - Hou,B
AU  - Vlontzos,A
AU  - Kainz,B
DO  - 10.1007/978-3-031-25066-8_42
EP  - 713
PY  - 2023///
SN  - 0302-9743
SP  - 704
TI  - Self-supervised 3D Human Pose Estimation in Static Video via Neural Rendering
UR  - http://dx.doi.org/10.1007/978-3-031-25066-8_42
ER  -
Download