<div dir="ltr"><div><div><div style="font-family:arial,helvetica,sans-serif;font-size:12pt;color:rgb(0,0,0)"><div>3D Human Pose Estimation from a Single Image with Deep Learning:<br></div><div><span class="gmail-Object" id="gmail-OBJ_PREFIX_DWT580_com_zimbra_url"><span class="gmail-Object" id="gmail-OBJ_PREFIX_DWT581_com_zimbra_url"><a target="_blank" href="https://jobs.inria.fr/public/classic/en/offres/2020-02493">https://jobs.inria.fr/public/classic/en/offres/2020-02493</a></span></span><br></div><div><br><strong>Context:</strong></div><div><br>The
engineer will work closely with Dr. Adnane Boukhayma and Prof. Franck
Multon. The work will be conducted at Inria Rennes in the MimeTIC
research team. This position takes part in the KIMEA Cloud project, a
collaboration between Inria Rennes and start-ups Moovency and Quortex.
The goal of this project is to asses the risk of musculoskeletal
disorders from a smartphone. The manufacturing industry is the sector
most affected by musculoskeletal disorders, in particular due to
repetitive gestures and frequent load transport. These companies do not
necessarily have internal ergonomics resources and cannot always invest
in technological tools. Given simply a video of the worker in his
workstation, a Deep Learning based algorithm will estimate the 3D
positions of the person’s joints. The musculoskeletal risks will be
subsequently analyzed automatically from these 3D postures. The role of
Inria in this project is to research and develop a robust solution for
3D human pose estimation from color images in the wild, particularly in
the industrial context.<br><br><strong>Assignment:</strong><br><br>3D
human pose estimation is one of the fundamental problems and most
active research areas in computer vision with various applications in
many fields such as action recognition, human-machine interfaces,
special effects and telepresence. Despite recent advances in the
scientific community, monocular 3D human pose estimation in natural
images remains far from being resolved. <br><br>The
recent surge of Deep Learning allowed a substantial improvement in the
performance of state-of-the-art methods on 2D and 3D human pose
estimation. In particular, a family of 3D pose estimators cast the
problem as lifting from 2D to 3D predictions (e.g. [1,2,3,4]). They
generally outperform the end-to-end counterparts since they benefit from
the remarkable current performances of 2D pose estimators, and due in
part to the lack of massive training image data with ground-truth 3D
pose annotations. We propose to follow this direction at first,
reproduce state-of-the-art results and explore further improvements and
new approaches to allow in particular better generalization to natural
images and challenging capture conditions, reducing dependencies to 2D
predictions, and using incremental learning to update the learned models
with new learning examples on the fly. <br><br>Within
this role, the engineer will lead the development of a deep learning
based method for 3D human pose estimation from a single color image.
He/she could also participate in the research part of the project. The
results of these works are expected be published in top tier computer
vision conferences such as CVPR, ICCV, ECCV, etc. <br><br>We propose the following course of action:<br>- 2D to 3D pose estimation lifting:<br>Developing
a Deep Learning method allowing to obtain 3D poses from 2D poses. This
task notably involves generating a simulated 2D/3D learning set from 3D
motion capture. The challenges are to be able to manage erroneous 2D
skeletons in the event of large occlusions, and the multitude of
possible 3D points of view.<br>- Combining end-to-end 3D pose estimation and 2D-3D lifting:<br>Developing
a Deep Learning method for 3D human pose estimation that can learn
simultaneously from image/3D, image/2D and 2D/3D annotation pairs. Test
cases include industrial postures and environments, as well as severe
capture conditions.<br>- Incremental learning:<br>Developing
a method that allows the learning models to adapt in an incremental way
to new learning data without forgetting their existing knowledge. The
objective is to avoid relaunching a total learning of the Deep Learning
network with each new example that we would like to add. <br><br>[1] Multi-person 2d and 3d pose detection in natural images. TPAMI, 2019.<br>[2] 3d human pose estimation = 2d pose estimation + matching. CVPR, 2017.<br>[3] A simple yet effective baseline for 3d human pose estimation. ICCV, 2017.<br>[4] 3d human pose estimation in the wild by adversarial learning. CVPR, 2018.<br><br><strong>Activities:</strong><br><br>The engineer will be tasked with:<br>-
Developing a program allowing 3D human pose estimation from single
color images in the wild. The solution will be tested on industrial use
cases with possible occlusions and extreme capture situations.<br>-
Depending on the progress of the project, developing an incremental
learning solution allowing the aforementioned 3D pose estimation model
to learn from new example cases without the need to retrain on all data,
and without any loss in the models performance. <br><br>In practice, these tasks imply:<br>- Participating in the research discussions and algorithms design.<br>- Reading and implementing research papers.<br>- Reproducing state-of-the-art results.<br>- Implementing the ideas proposed by the research collaborators.<br>- Creating training and testing datasets.<br>- Participating in the publication of the research results. <br><br><strong>Skills:</strong> <br><br>-
Candidates should preferably have a MSc or PhD in computer science,
applied mathematics, computer vision, computer graphics or machine
learning. <br>- The ability to read, understand and implement research papers and reproduce scientific results.<br>- Good coding skills (Python, C, C++).<br>- Proficiency in deep learning frameworks such as Pytorch is a plus. <br> <br><strong>The keys to success:</strong><br><br>We
are looking for excellent candidates, preferably with a solid
background in mathematics or computer science and good coding skills,
who can work independently and who are also keen to collaborate with
other researchers. <br></div></div></div></div></div>