| Ginger Delmas, Philippe Weinzaepfel, Thomas Lucas, Francesc Moreno-Noguer, Gregory Rogez |
| European Conference on Computer Vision (ECCV), Tel Aviv, Israel, 23–27 October, 2022 |
Text can be used to improve semantic understanding of human poses.
Gaining semantic understanding of human poses would open the door to a number of applications such as pose teaching, pseudo 3D annotation when deploying a MoCap system is complicated, digital pose generation, or search for complex poses in large-scale datasets.
For this purpose, we introduce the PoseScript dataset, which pairs a few thousand 3D human poses from AMASS[2] with rich human-annotated descriptions of the body parts and their spatial relationships. To increase the size of this dataset to a scale compatible with typical data hungry learning algorithms, we propose an elaborate captioning process that generates automatic synthetic descriptions in natural language from given 3D keypoints. We show applications of the PoseScript dataset to retrieval of relevant poses from large-scale datasets and to synthetic pose generation, both based on a textual pose description.
The PoseScript dataset is composed of:
The automatically generated captions won’t provide any cultural references, but will me more detailed, eg. “the right knee is forming a L shape”.
We design a text-to-pose retrieval model, where the encodings of the pose and its corresponding PoseScript description are brought close together in a joint embedding space, while elements from different data pairs are pushed apart.
As a consequence, one can freely type a description text to query poses from a large database by looking at embedding similarity.
It also makes it possible to retrieve images showing people in particular poses, provided that the images[4] are associated with SMPL body fits[5].
Next, we design a text-conditioned pose generation model, such that, at test time, the text is encoded as a distribution, from which we sample a z that will then be decoded as a 3D body pose.
At train time, we also encode the initial pose, and sample from the corresponding distribution to decode it as a new pose, that will be compared to the initial pose, as in a regular variational auto-encoder. To make the model conditioned on text, we force the two distributions of pose and text to be aligned. We additionally regularize the pose distribution so to sample poses without conditioning on text.
As a result, for a given input pose description, one can obtain several different pose generations. The more detailed the description, the less diverse the different generated poses.
[1] https://en.wikipedia.org/wiki/Downward_Dog_Pose
[2] AMASS: Archive of Motion Capture as Surface Shapes, Mahmood et al., ICCV 2019
[3] https://www.mturk.com/
[4] Microsoft COCO: Common Objects in Context, Lin et al., ECCV 2014
[5] Exemplar fine-tuning for 3D human model fitting towards in-the-wild 3D human pose estimation, Joo et al., 3DV 2020
@inproceedings{posescript, title={{PoseScript: 3D Human Poses from Natural Language}}, author={{Delmas, Ginger and Weinzaepfel, Philippe and Lucas, Thomas and Moreno-Noguer, Francesc and Rogez, Gr\’egory}}, booktitle={{ECCV}}, year={2022} }
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimization problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimization to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments. More details on our research can be found in the Explore section below.
For a robot to be useful it must be able to represent its knowledge of the world, share what it learns and interact with other agents, in particular humans. Our research combines expertise in human-robot interaction, natural language processing, speech, information retrieval, data management and low code/no code programming to build AI components that will help next-generation robots perform complex real-world tasks. These components will help robots interact safely with humans and their physical environment, other robots and systems, represent and update their world knowledge and share it with the rest of the fleet. More details on our research can be found in the Explore section below.
Visual perception is a necessary part of any intelligent system that is meant to interact with the world. Robots need to perceive the structure, the objects, and people in their environment to better understand the world and perform the tasks they are assigned. Our research combines expertise in visual representation learning, self-supervised learning and human behaviour understanding to build AI components that help robots understand and navigate in their 3D environment, detect and interact with surrounding objects and people and continuously adapt themselves when deployed in new environments. More details on our research can be found in the Explore section below.
Details on the gender equality index score 2024 (related to year 2023) for NAVER France of 87/100.
The NAVER France targets set in 2022 (Indicator n°1: +2 points in 2024 and Indicator n°4: +5 points in 2025) have been achieved.
—————
Index NAVER France de l’égalité professionnelle entre les femmes et les hommes pour l’année 2024 au titre des données 2023 : 87/100
Détail des indicateurs :
Les objectifs de progression de l’Index définis en 2022 (Indicateur n°1 : +2 points en 2024 et Indicateur n°4 : +5 points en 2025) ont été atteints.
Details on the gender equality index score 2024 (related to year 2023) for NAVER France of 87/100.
1. Difference in female/male salary: 34/40 points
2. Difference in salary increases female/male: 35/35 points
3. Salary increases upon return from maternity leave: Non calculable
4. Number of employees in under-represented gender in 10 highest salaries: 5/10 points
The NAVER France targets set in 2022 (Indicator n°1: +2 points in 2024 and Indicator n°4: +5 points in 2025) have been achieved.
——————-
Index NAVER France de l’égalité professionnelle entre les femmes et les hommes pour l’année 2024 au titre des données 2023 : 87/100
Détail des indicateurs :
1. Les écarts de salaire entre les femmes et les hommes: 34 sur 40 points
2. Les écarts des augmentations individuelles entre les femmes et les hommes : 35 sur 35 points
3. Toutes les salariées augmentées revenant de congé maternité : Incalculable
4. Le nombre de salarié du sexe sous-représenté parmi les 10 plus hautes rémunérations : 5 sur 10 points
Les objectifs de progression de l’Index définis en 2022 (Indicateur n°1 : +2 points en 2024 et Indicateur n°4 : +5 points en 2025) ont été atteints.
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
FunctionalThis website uses functional cookies which are required for the search function to work and to apply for jobs and internships.
AnalyticalOur website uses analytical cookies to make it possible to analyse our website and optimize its usability.
Social mediaOur website places social media cookies to show YouTube and Vimeo videos. Cookies placed by these sites may track your personal data.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.
