Technology Transfer Project

Text4Pose: Leveraging text to improve human pose, shape, motion estimation and generation

Type

Technology Transfer Contract

Start Date

15/09/2021

End Date

14/10/2025

Default project illustration

Staff

Project Description

The goal of the project is to study how text information can be leveraged in order to improve problems related to human pose: estimating human pose and shape in images or in videos, as well as predicting future human motion.

This project is a collaboration between IRI and Naver Labs Europe.

Project Publications

Conference Publications

  • G.D. Delmas, P. Weinzaepfel, F. Moreno-Noguer and G. Rogez. PoseFix: correcting 3D human poses with natural language, 2023 International Conference on Computer Vision, 2023, Paris, France, pp. 14972-14982.

    Open/Close abstract Abstract Info Info pdf PDF

  • G.D. Delmas, P. Weinzaepfel, T. Lucas, F. Moreno-Noguer and G. Rogez. PoseScript: 3D human poses from natural language, 17th European Conference on Computer Vision, 2022, Tel Aviv (Israel), in Computer Vision – ECCV 2022 , Vol 13666 of Lecture Notes in Computer Science, pp. 346-362, 2022.

    Open/Close abstract Abstract Info Info pdf PDF