Manuel J. Marin-Jimenez (University of Cordoba, Spain)
Javier Romero (Amazon, Spain) email@example.com
Hao Li (Pinscreen Inc.; University of Southern California; USC Institute for Creative Technologies) firstname.lastname@example.org
Gregory Rogez (Naver Labs, France), email@example.com
Current computer vision algorithms and deep learning-based methods can detect people in images and estimate their 2D pose with a remarkable accuracy. However, understanding humans and estimating their pose and shape in 3D is still an open problem. The ambiguities in lifting 2D pose to 3D, the lack of annotated data to train 3D pose regressors in the wild and the absence of a reliable evaluation dataset in real world situations make the problem very challenging.
Since very recent papers achieved impressive results in tasks like body reposing using purely 2D based techniques, we would also like to challenge the need of explicit 3D techniques and data in such computer vision problems related to humans.
Therefore, we aim at gathering high quality publications of researchers who work on 3D human pose estimation from RGB images and videos, and related topics such as 3D human shape estimation from images or activity recognition from 3D skeletal data.
Topics of Interest
We encourage researchers to study and develop novel computer vision methods that help to boost the fields of human pose estimation, motion and activity recognition, and shape reconstruction in 3D.
More precisely, the relevant topics for this special issue include (but are not limited to):
- 3D human pose estimation (full-body, upper-body, hands) in images and videos
- 3D human shape estimation
- 3D articulated pose tracking
- 3D pose from 2D pose
- 3D pose/shape modelling and rendering
- Future 3D pose prediction
- 3D action recognition (from 3D skeletal data)
- Gesture interfaces
- Synthetic data and data annotation for 3D human pose
- Structured prediction, regression, and other relevant theories/algorithms
- Applications of body pose estimation in AR/VR
- Applications of body pose estimation in robotics
- Multi-person 3D pose from images
Full paper submission deadline: 15 September 2020
First review notification: 30 November 2020 Revised paper due: 1 March 2021
Final decisions: 1 April 2021
Paper submission and review
Submitted papers should present original, unpublished work, relevant to one of the topics of the Special Issue. All submitted papers will be evaluated on the basis of relevance, significance of contribution, technical quality, scholarship, and quality of presentation, by at least three independent reviewers. It is the policy of the journal that no submission, or substantially overlapping submission, be published or be under review at another journal or conference at any time during the review process. Manuscripts will be subject to a peer reviewing process and must conform to the author guide lines available on the IJCV website at: https://www.springer.com/11263 .
Do not forget to select “S.I.: Human Pose, Motion, Activities, and Shape in 3D” at the beginning of the submission process.
Inquiries can be addressed to: firstname.lastname@example.org, email@example.com, firstname.lastname@example.org
Authors are encouraged to submit high-quality, original work that has neither appeared in, nor is under consideration by other journals.
All papers will be reviewed following standard reviewing procedures for the Journal.
Papers must be prepared in accordance with the Journal guidelines: www.springer.com/11263
Springer provides a host of information about publishing in a Springer Journal on our Journal Author Resources page, including FAQs, Tutorials along with Help and Support.
Other links include: