Eckhardt
-
-
Too many holiday cookies will give you nightmares. An anonymous fear submitted to Deep Dark Fears - thanks! You can find my DDF books wherever books are sold!
-
Bill Tavis: Recent Work
Cross Connect favorite Bill Tavis lives in Austin, TX and makes his living self-publishing fractal posters (www.mandelmap.com), painting murals, selling fine art prints, and doing commissions. Despite gifs not being part of his income, he is dedicated to gif art, and has made over 500 and continues to make them. He assured me that he will continue to do so: ‘there’s now a backlog of GIFs wanting to get out of my brain so you can count on seeing more at some point!’
We look forward to seeing them Bill!
More unique art on Cross Connect Magazine:
Twitter || Facebook || Instagram
Posted by David(via billtavis)
-
-
Art class !
Also next time I will put more frames to the end, forgot that Tumblr make the videos loops so last frames goes fast, will thing about it for now :)!
Thanks to many for telling and thanks for enjoying my work!
-
Hey, this post may contain adult content, so we’ve hidden it from public view.
-
-
It is what it is
-
style2paints V4
Project from lllyasviel is latest version of web app that automatically colourizes a line drawing in the style of another painted illustration
The AI can paint on a sketch accroding to a given specific color style.
The author of this article is not skilled at color or painting.
All the colorization results are obtained by clicking buttons or canvases.
A video demonstration can be found at bilibili here
An intro can be found here, or if you want to dive right in you can go here
-
3D Face Reconstruction from a Single Image
Machine Learning research from University of Nottingham School of Computer Science can generate a 3D model of a human face from an image using neural networks:
3D face reconstruction is a fundamental Computer Vision problem of extraordinary difficulty. Current systems often assume the availability of multiple facial images (sometimes from the same subject) as input, and must address a number of methodological challenges such as establishing dense correspondences across large facial poses, expressions, and non-uniform illumination. In general these methods require complex and inefficient pipelines for model building and fitting. In this work, we propose to address many of these limitations by training a Convolutional Neural Network (CNN) on an appropriate dataset consisting of 2D images and 3D facial models or scans. Our CNN works with just a single 2D facial image, does not require accurate alignment nor establishes dense correspondence between images, works for arbitrary facial poses and expressions, and can be used to reconstruct the whole 3D facial geometry (including the non-visible parts of the face) bypassing the construction (during training) and fitting (during testing) of a 3D Morphable Model. We achieve this via a simple CNN architecture that performs direct regression of a volumetric representation of the 3D facial geometry from a single 2D image. We also demonstrate how the related task of facial landmark localization can be incorporated into the proposed framework and help improve reconstruction quality, especially for the cases of large poses and facial expressions.
There is an online demo which will let you upload an image to convert and even save as a 3D model here