• UCSBgauchos twitter avatar
    UCSB Takes 2-Game Winning Streak into Friday Night Thunderdome Matchup Against Prairie View https://t.co/X2Bq5NQMHa
    2 hours 41 min ago
  • UCSBLibrary twitter avatar
    Thankful for beautiful sunsets that paint the sky. Safe travels and Happy Thanksgiving, #Gauchos! https://t.co/pz7GrusWaF
    7 hours 40 min ago
  • brenucsb twitter avatar
    Americans discarded the equivalent of 6 million #turkeys over #Thanksgiving last year. This year, see how you can h… https://t.co/BHWeNKZXNs
    8 hours 40 min ago
  • ucsantabarbara twitter avatar
    What's new this week on #GauchoCourses? Comm 178: The Dark Side of Comm! https://t.co/RW08u8Ayve
    11 hours 39 min ago
  • AS_UCSB twitter avatar
    Happy Thanksgiving! https://t.co/S57dk4gbse
    11 hours 53 min ago

Intelligent Animation

UCSB engineers, Disney Research and Pixar Animation Studios collaborate to incorporate AI into a computer-based rendering system
Wednesday, July 26, 2017 - 09:15
Santa Barbara, CA

Bako_UCSBPressReleaseTeaser.jpg

AI denoising

A before-and-after image of the denoising capability of the AI neural network model

Photo Credit: 

Steve Bako

Modern films and TV shows are filled with spectacular computer-generated sequences computed by rendering systems that simulate the flow of light in a three-dimensional scene and convert the information into a two-dimensional image. But computing the thousands of light rays (per frame) to achieve accurate color, shadows, reflectivity and other light-based characteristics is a labor-intensive, time-consuming and expensive undertaking. An alternative is to render the images using only a few light rays. That saves time and labor but results in inaccuracies that show up as objectionable “noise” in the final image.

UC Santa Barbara electrical and computer engineering Ph.D. student Steve Bako and his advisor, Pradeep Sen, are advancing on a solution. Over the past couple of years, the two have worked with researchers at Disney Research and Pixar Animation Studios to develop a new technology based on artificial intelligence (AI) and deep learning to eliminate that noise and enable production-quality rendering at much higher speeds. Bako will present the findings at the SIGGRAPH conference, the premier venue for technical research in computer graphics, to be held July 31-August 3 in Los Angeles.

Bako spent a year working at Pixar. The team tested the software by using millions of examples from the film “Finding Dory” to train a deep-learning model known as a convolutional neural network. Through this process, the system learned to transform noisy images into noise-free versions that resemble those computed with significantly more light rays. Once trained, the system successfully removed the noise on test images from entirely different films, such as Pixar’s latest release, “Cars 3,” and their upcoming feature “Coco,” even though they had completely disparate styles and color palettes.

“Noise is a really big problem for production rendering,” said Tony DeRose, head of research at Pixar. “This new technology allows us to automatically remove the noise while preserving the detail in our scenes.”

The work presents a significant step forward over previous state-of-the-art denoising methods, which often left artifacts or residual noise that required artists to either render more light rays or to tweak the denoising filter to improve the quality of a specific image. Disney and Pixar plan to incorporate the technology in their production pipelines to accelerate the movie-making process.

“Other approaches for removing image noise have grown increasingly complex, with diminishing returns,” said Markus Gross, vice president for research at Disney Research. “By leveraging deep learning, this work presents an important step forward for removing undesirable artifacts from animated films.”

To facilitate further exploration of this exciting area, the team will make their code and the deep learning model’s trained weights available to the research community.

Contact Info: 

Pradeep Sen
(805) 893-4265
psen   at   ece.ucsb.edu

James Badham
(805) 893-3648
jbadham@engineering.ucsb.edu

Topics: