Generating Hair Strands From Single-View Input
Subscribe:  iCal  |  Google Calendar
7, Mar — 1, Jun
San Jose US   17, Mar — 22, Mar
San Francisco US   18, Mar — 23, Mar
San Francisco US   18, Mar — 23, Mar
York US   26, Mar — 29, Mar
Latest comments
by crowbringer
5 hours ago

This priest surely committed to his celibate there...

Cheap art will be just that. The true value lies in commitment and hard work. This is just a tool and without a creative mind operating it the results will hold no magic. Did photography kill painting? I think both are doing and developing rather well.

by Mark
6 hours ago

Very insightful. Thanks!

Generating Hair Strands From Single-View Input
7 October, 2018

Let’s check out a novel method that automatically generates 3D hair strands from a variety of single-view input. The approach was originally described in a paper “3D Hair Synthesis Using Volumetric Variational Autoencoders” by Shunsuke Saito, Liwen Hu, Chongyang Ma, Linjie Luo, and Hao Li. 

Instead of using a large collection of 3D hair models directly, the team proposed using a compact latent space of a volumetric variational autoencoder (VAE). This deep neural network, trained with volumetric orientation field representations of 3D hair models, is said to be able to synthesize new hairstyles from a compressed code.

Input image, volumetric representation with color-coded local orientations predicted by the method, the final synthesized hair strands rendered from two viewing points.

“To enable end-to-end 3D hair inference, we train an additional regression network to predict the codes in the VAE latent space from any input image. Strand-level hairstyles can then be generated from the predicted volumetric representation. Our fully automatic framework does not require any ad-hoc face fitting, intermediate classification and segmentation, or hairstyle database retrieval,” said the team.

The researchers state that their hair synthesis approach is significantly more robust than state-of-the-art data-driven hair modeling techniques. The storage requirements here are said to be minimal and you can produce a 3D hair model from an image in a second. The techniques also allows to produce models from highly stylized cartoon images, non-human subjects, and pictures taken from the back of a person.

Make sure to get more details and check out the full paper here

Leave a Reply