Abstract
Garments are highly detailed and dynamic objects made up of particles that interact with each other and with other objects, making the task of 2D to 3D garment reconstruction extremely challenging. Therefore, having a lightweight 3D representation capable of modelling fine details is of great importance. This work presents a deep learning framework based on Generative Adversarial Networks (GANs) to reconstruct 3D garment models from a single RGB image. It has the peculiarity of using UV maps to represent 3D data, a lightweight representation capable of dealing with high-resolution details and wrinkles. With this model and kind of 3D representation, we achieve state-of-the-art results on the CLOTH3D++ dataset, generating good quality and realistic garment reconstructions regardless of the garment topology and shape, human pose, occlusions and lightning.
Original language | English |
---|---|
Title of host publication | Proceedings - 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2021 |
Editors | Vitomir Struc, Marija Ivanovska |
Publisher | IEEE Signal Processing Society |
Publication date | 2021 |
ISBN (Electronic) | 9781665431767 |
DOIs | |
Publication status | Published - 2021 |
Externally published | Yes |
Event | 16th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2021 - Virtual, Jodhpur, India Duration: 15 Dec 2021 → 18 Dec 2021 |
Conference
Conference | 16th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2021 |
---|---|
Country/Territory | India |
City | Virtual, Jodhpur |
Period | 15/12/2021 → 18/12/2021 |
Series | Proceedings - 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2021 |
---|
Bibliographical note
Funding Information:VI. ACKNOWLEDGMENTS This work has been partially supported by the Spanish project PID2019-105093GB-I00 (MINECO/FEDER, UE) and CERCA Programme/Generalitat de Catalunya.) This work is partially supported by ICREA under the ICREA Academia programme and Amazon Research Awards.
Publisher Copyright:
© 2021 IEEE.