@inproceedings{DBLP:conf/eccv/SchmidtkeHVK22,
  author       = {Luca Schmidtke and
                  Benjamin Hou and
                  Athanasios Vlontzos and
                  Bernhard Kainz},
  title        = {Self-supervised 3D Human Pose Estimation in Static Video via Neural
                  Rendering},
  booktitle    = {{ECCV} Workshops {(3)}},
  series       = {Lecture Notes in Computer Science},
  volume       = {13803},
  pages        = {704--713},
  publisher    = {Springer},
  year         = {2022},
  doi = {10.1007/978-3-031-25066-8\_42},
  eprint = {2210.04514},
  archiveprefix = {arXiv},
  abstract = {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.},
}