Friday, December 15, 2017

Digging in the Front Yard


When I was a kid growing up in Los Altos, California, I dug holes in my front yard looking for a lost civilization or a new dinosaur. My friends’ mothers wouldn’t let them play with me after school because they came home with their pockets full of dirt. I went on to major in anthropology at UC Berkeley and joined real archaeological and paleo excavations. My childhood dreams came true when I was sent on assignment by National Geographic to travel to dig sites with archaeologists to help them reconstruct life in the ancient world.
-----

Thursday, December 14, 2017

I'll be teaching next summer at IMC

Art by Kent Williams
Join me in the summer of 2018 for a workshop in Massachusetts called IMC, (also known as Illustration Master Class) 

At IMC you spend the week painting with instructors from the realm of Imaginative Realism: Julie BellDonato GiancolaBoris Vallejo, Greg ManchessScott M FischerDan Dos Santos, Irene Gallo Tara McPherson Kent Williams and me, James Gurney! There are just a handful of spots left.

IMC (aka Illustration Master Class)

Proposed Rockwell Sale Under Investigation

(Stephan Schuetze/Bild Zeitung via Getty Images, link)
Secret documents reveal that the Berkshire Museum was pressured to sell off their Norman Rockwell originals by a Boston consulting firm. 

For now, the planned liquidation of their most valuable and beloved artwork has been been halted by the Massachusetts Attorney General as the investigation continues.  

Let us hope that Sotheby's will release the Museum from their fees if the Museum decides to call off the sale and raise money the old fashioned way—by showing great art to the community and asking for their support.

More on ArtNet

Wednesday, December 13, 2017

Curvature Blindness Illusion


A series of paired lines passes through areas of white, grey, and black. The lines remain the same throughout. They have a consistent wavy (sinusoidal) shape. 

The difference between the sets is the placement of light and dark segments: one set has the tone change at the bottom of the curve.

As the sets of lines pass through the grey area, some of them seem to take on an angular, zig-zag quality. The effect is extremely compelling.

Psychologist Kohske Takahashi of Chukyo University of Japan discovered the illusion. He suggests that when the brain's visual system is faced with ambiguous cues about whether it's seeing curved or straight-segmented lines, it favors the angular cues:

"The underlying mechanisms for the gentle curve perception and those of obtuse corner perception are competing with each other in an imbalanced way and the percepts of corner might be dominant in the visual system."
-----
More:
For a high level discussion, read the comments after the Discover Magazine blog post.
Thanks to several of you who let me know about this.

Tuesday, December 12, 2017

Animation Tests



(Link to video)  Here are a few animation tests — Sprocket runs,  eats paper,  and Clement grabs some power ups.


Here's a still frame showing the motion blur and live-action dynamics captured in-camera.

Monday, December 11, 2017

Image Translation

A new machine-learning algorithm can take a photo of a street scene and translate the image to another time of day or another weather condition. 


For example, the photo on the left shows is taken from a car on a rainy day. On the right, the computer translates the scene into a sunny day with a blue sky. 


Here the algorithm does the opposite, translating a photo of a sunny day (left) into a virtual image of the same scene in rainy conditions (right).


The night-to-day translations are impressive because there seems so little information to start with in the photo at left, and the change is so radical.


The system can also translate a photographic street scene into a graphic that looks like it comes from a video game — or it can take a still from a video game and make it look more photographic. 

It can also change the hair color of a person, or alter a dog from one breed to another. 

This machine-learning technology, driven by generative adversarial networks, is progressing very quickly, so any weaknesses or limitations we see in the results now will be overcome rapidly.

We can no longer say "Photos don't lie." 
-----
Read More:
Google photo collection with lots more pairs of examples.
Scientists' paper as a PDF
Video Game Graphics To Reality And Back

Related Posts
Text-to-Image Synthesis
Generative design resembles Art Nouveau
Morphing Celebrities