3DBodyTex.v2

Is an extension of 3DBodyTex.v1. It contains about 3000 static 3D human scans with high-resolution texture. It features a large variety of poses and clothing types, with about 500 different subjects. Each subject is captured in about 3 poses. Most subjects perform the corresponding poses in both standard close-fitting clothing and arbitrary casual clothing. It has been used in Shape Recovery from Partial Textured 3D Scans Challenge (SHARP in conjunction with ECCV 2020) [*].

[*] Saint, A., Kacem, A., Cherenkova, K., Papadopoulos, K., Chibane, J., Pons-Moll, G., Gusev, G., Foffi, D., Aouada, D., Ottersten, B. (2020). SHARP 2020: The 1st Shape Recovery from Partial Textured 3D Scans Challenge Results, SHARP workshop, ECCV 2020.

Requesting 3DBodyTex.v2

The 3DBodyTex.v2 dataset is available for use by external parties. Due to agreements signed by the volunteer models, a license agreement must be requested and signed by the recipient and the research administration office director of your institution before the data can be provided. To make a request for the data, please contact us on Shapify3D (at) uni (dot) lu or use the following contact form.

Note:

(1) Once a license agreement is signed, we will give access to download the data.

(2) If this data is used, in whole or in part, the following paper must be referenced:

3DBodyTex: Textured 3D Body Dataset, Saint, Alexandre Fabian AAhmed, EmanShabayek, Abd El RahmanCherenkova, KseniyaGusev, GlebAouada, DjamilaOttersten, Björn, in 2018 Sixth International Conference on 3D Vision (3DV 2018) (2018).

Bodyfitr: Robust Automatic 3D Human Body Fitting, Saint, Alexandre Fabian AShabayek, Abd El RahmanCherenkova, KseniyaGusev, GlebAouada, DjamilaOttersten, Björn, in IEEE International Conference on Image Processing (ICIP 2019).

SHARP 2020: The 1st Shape Recovery from Partial Textured 3D Scans Challenge Results, Saint, A., Kacem, A., Cherenkova, K., Papadopoulos, K., Chibane, J., Pons-Moll, G., Gusev, G., Foffi, D., Aouada, D., Ottersten, B. (2020). SHARP workshop, ECCV 2020.

    Research Teams

    Related Publications

    This work was funded by the National Research Fund (FNR), Luxembourg, AFR PPP reference 11806282, and by Artec Europe SARL. The authors are grateful to the volunteers for the scanning, to the whole Computer Vision Lab at SnT for collecting the data, and to the contributors of the open source libraries used in this work.