Researchers use AI to generate 3D avatars from text to enable virtual fitting and shape editing

News on September 15: Recently, researchers announced two new research results that use artificial intelligence to generate three-dimensional avatars, realizing applications such as virtual fitting and avatar shape editing. These results come from researchers at the Max Planck Institute in Germany and other institutions, and have been published on arXiv

The first study proposes a method called DELTA that can create three-dimensional avatars with independent body and clothing/hair layers. The researchers used different 3D representations to model the body and clothing/hair separately, creating avatars from monocular RGB videos. This decomposition enables applications such as virtual fitting and shape editing, where clothes and hair can be easily converted between different body types.

The second study proposed a text-to-avatar method named TECA using stable diffusion and DELTA hybrid 3D representation. This method can generate high-quality avatars from text descriptions only and enable powerful attribute editing. The system first uses stable diffusion to generate facial images as a reference, and then adds hair, clothes and other elements in sequence. The researchers said that the quality of the synthetic avatars generated by this method is significantly improved, and the attribute transfer enables powerful editing capabilities.

These two studies provide new ideas for digital human generation. Using artificial intelligence algorithms to deconstruct the different components of digital humans can not only create realistic three-dimensional virtual images, but also support applications such as online virtual fittings, which will have a profound impact on fashion e-commerce, social platforms and the metaverse.

What needs to be rewritten is: [Quoted from: Webmaster’s Home]

The above is the detailed content of Researchers use AI to generate 3D avatars from text to enable virtual fitting and shape editing. For more information, please follow other related articles on the PHP Chinese website!