[visionlist] 3DHumans Dataset Release -Free high quality human mesh data with diverse clothing for research.

Avinash Sharma avinash.sn.sharma at gmail.com
Tue Jan 24 05:54:27 -04 2023

Dear all,

I would like to announce the release of our new high quality "3DHumans"
dataset for Human Body Models with rich geometry and textural details as
well as loose oriental clothing.  The 3DHumans dataset provides around *180*
 meshes of people in diverse body shapes in various garments styles and
sizes. We cover a wide variety of clothing styles, ranging from loose robed
clothing, like saree (a typical South-Asian dress) to relatively tight fit
clothing, like shirts and trousers. Along with the high quality geometry
(mesh) and texture map, we also provide registered SMPL and semantic
segmentation. The faces of the subjects are blurred and smoothened out to
maintain privacy of volunteers.

The dataset is collected using *Artec Eva*
<https://www.artec3d.com/portable-3d-scanners/artec-eva-v2> hand held
structured light scanner. The scanner has 3D point accuracy up to 0.1 mm
and 3D resolution of 0.5 mm, enabling capture of high frequency geometrical
details, alongwith high resolution texture maps. The subjects were scanned
in a studio environment with controlled lighting and uniform illumination.

Please visit our webpage to access our 3DHumans dataset:

Please refer to our group webpage <https://3dcomputervision.github.io/> for
related research papers with focus on Human Body Digitization, Learnable
Texture Mapping, Garment Digitization, 4D Dynamic capture of Humans. We are
open to academic and industrial collaboration for propelling research in 3D
Vision domains. A high quality dynamic motion capture data with rich 3D
geometry is also planned to be released in the upcoming months. We are also
hiring research students, RA to our group so feel free to apply.

Please reach out to us if you have query related to dataset on

Avinash Sharma
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20230124/4b20506d/attachment.html>

More information about the visionlist mailing list