Tag: Disney Research

New Software Can Actually Edit Actors’ Facial Expressions

FaceDirector can seamlessly blend several takes to create nuanced blends of emotions, potentially cutting down on the number of takes necessary in filming.

Read more

Disney’s Augmented Reality Characters from Colored Drawings

Given the proliferation and popularity of digital devices, real-world activities like coloring can seem unexciting, and children become less engaged in them. Augmented reality holds unique potential to impact this situation by providing a bridge between real-world activities and digital enhancements.

Read more

Development of a Bipedal Robot that Walks Like an Animation Character

From Disney Research.

Authors
Seungmoon Song (Disney Research Pittsburgh)
Joohyung Kim (Disney Research Pittsburgh)
Katsu Yamane (Disney Research Pittsburgh)

IEEE International Conference on Robotics and Automation (ICRA) 2015

May 26, 2015

Our goal is to bring animation characters to life in the real world. We present a bipedal robot that looks like and walks like an animation character. We start from animation data of a character walking. We develop a bipedal robot which corresponds to lower part of the character following its kinematic structure. The links are 3D printed and the joints are actuated by servo motors. Using trajectory optimization, we generate an open-loop walking trajectory that mimics the character’s walking motion by modifying the motion such that the Zero Moment Point stays in the contact convex hull. The walking is tested on the developed hardware system.

Download File “Development of a Bipedal Robot that Walks Like an Animation Character-Paper”
[PDF, 1.42 MB]

Disney Research Automatic Editing of Footage from Multiple Social Cameras

Disney Research demonstrated Automatic Editing of Footage from Multiple Social Cameras at SIGGRAPH.

Video cameras that people wear to record daily activities are creating a novel form of
creative and informative media. But this footage also poses a challenge: how to expeditiously
edit hours of raw video into something watchable. One solution, according to Disney researchers,
is to automate the editing process by leveraging the first-person viewpoints of multiple cameras
to find the areas of greatest interest in the scene.

The method they developed can automatically combine footage of a single event shot by
several such “social cameras” into a coherent, condensed video. The algorithm selects footage
based both on its understanding of the most interesting content in the scene and on established
rules of cinematography.

“The resulting videos might not have the same narrative or technical complexity that a
human editor could achieve, but they capture the essential action and, in our experiments, were
often similar in spirit to those produced by professionals,” said Ariel Shamir, an associate
professor of computer science at the Interdisciplinary Center, Herzliya, Israel, and a member of
the Disney Research Pittsburgh team.

Whether attached to clothing, embedded in eyeglasses or held in hand, social cameras
capture a view of daily life that is highly personal but also frequently rough and shaky. As more
– more –eople begin using these cameras, however, videos from multiple points of view will be
available of parties, sporting events, recreational activities, performances and other encounters.

“Though each individual has a different view of the event, everyone is typically looking
at, and therefore recording, the same activity – the most interesting activity,” said Yaser Sheikh,
an associate research professor of robotics at Carnegie Mellon University. “By determining the
orientation of each camera, we can calculate the gaze concurrence, or 3D joint attention, of the
group. Our automated editing method uses this as a signal indicating what action is most
significant at any given time.”

In a basketball game, for instance, players spend much of their time with their eyes on the
ball. So if each player is wearing a head-mounted social camera, editing based on the gaze
concurrence of the players will tend to follow the ball as well, including long passes and shots to
the basket.

The algorithm chooses which camera view to use based on which has the best quality
view of the action, but also on standard cinematographic guidelines. These include the 180-
degree rule – shooting the subject from the same side, so as not to confuse the viewer by the
abrupt reversals of action that occur when switching views between opposite sides.

Avoiding jump cuts between cameras with similar views of the action and avoiding very
short-duration shots are among the other rules the algorithm obeys to produce an aesthetically
pleasing video.
The computation necessary to achieve these results can take several hours. By contrast,
professional editors using the same raw camera feeds took an average of more than 20 hours to
create a few minutes of video.

The algorithm also can be used to assist professional editors tasked with editing large
amounts of footage.

Other methods available for automatically or semi-automatically combining footage from
multiple cameras appear limited to choosing the most stable or best lit views and periodically
switching between them, the researchers observed. Such methods can fail to follow the action
and, because they do not know the spatial relationship of the cameras, cannot take into
consideration cinematographic guidelines such as the 180-degree rule and jump cuts.

Automatic Editing of Footage from Multiple Social Cameras
Arik Shamir (DR Boston), Ido Arev (Efi Arazi School of Computer Science), Hyun Soo Park (CMU), Yaser Sheikh (DR Pittsburgh/CMU), Jessica Hodgins (DR Pittsburgh)
ACM Conference on Computer Graphics & Interactive Techniques (SIGGRAPH) 2014 – August 10-14, 2014
Paper [PDF, 25MB]

Lucid Dreams of Gabriel – Teaser

From Variety,

Disney and Swiss pubcaster SRF unveil experimental short at Locarno fest.

At the Locarno Film Festival, the Disney lab and SRF jointly unveiled an impressive experimental short titled “Lucid Dreams of Gabriel” (see teaser) which for the first time displayed local frame variation, local pixel timing, super slow motion effects, and a variety of artistic shutter functions showcasing this “The Flow-of-Time” technique.

The project was created by the Disney Research lab in tandem with the formidable computer graphics lab at the Swiss Federal Institute of Technology Zurich (ETH) with SRF providing studio space, personnel, and other resources.

“We wanted to control the perception of motion that is influenced by the frame rate (how many images are shown per second) as well as by the exposure time,” said Markus Gross, who is Vice President Research, Disney Research and director of Disney Research, Zurich, at the presentation.

Use of the new technologies in the short, which is a surreal non-linear story about a mother achieving immortality in her son’s eyes after an accident in the spectacular Engadin Alpine valley, allowed director Sasha A. Schriber to avoid using green screen and to make the transition from reality (at 24 frames per second) to a supernatural world (at 48 frames per second).

“Lucid Dreams Of Gabriel,” an experimental short film created by Disney Research in collaboration with ETH, Zurich, was shot at 120fps/RAW with all effects invented and applied in-house at Disney Research Zurich. We sought to produce a visual effects framework that would support the film’s story in a novel way. Our technique, called “The Flow-Of-Time,” includes local frame rate variation, local pixel timing and a variety of artistic shutter functions.

Effects include:
•High dynamic range imaging
•Strobe and rainbow shutters
•Global and local framerate variations
•Flow motion effects
•Super slow motion
•Temporal video compositing

The following scenes of the teaser, indicated by the timecode, demonstrate different components of our new technology:

Shots with a dark corridor and a window (0:08); a man sitting on a bed (0:16):
Our new HDR tone-mapping technique makes use of the full 14 bit native dynamic range of the camera to produce an image featuring details in very dark as well as very bright areas at the same time. While previous approaches have been mostly limited to still photography or resulted in artifacts such as flickering, we present a robust solution for moving pictures.

A hand holding a string of beads (0:14):
As we experimented with novel computational shutters, the classic Harris-shutter was extended to make use of the full rainbow spectrum instead of the traditional limitation to just red, green, and blue. For this scene, the input was rate converted using our custom technology, temporally split and colored, then merged back into the final result.

The double swings scene (0:20):
Extending on our experiments with computational shutters, this scene shows a variety of new techniques composed into a single shot. Fully facilitating the original footage shot in 120 fps, the boy has been resampled at a higher frame rate (30fps) and a short shutter, resulting an ultra crisp, almost hyper-real appearance, while the woman was drastically resampled at a lower frame rate (6fps) featuring an extreme shutter which is physically not possible and adding a strong motion blur to make her appear more surreal.

Car driving backwards and a flower (0:30); a train (0:36),
For these scenes, we were experimenting with extreme computational shutters. The theoretical motion blur for the scenes was extended with a buoyancy component and modified through a physical fluid simulation, resulting in physically impossible motion blur. As shown, it is possible to apply this effect selectively on specific parts of the frame, as well as varying the physical forces.

Super slow motion closeup of the boy (0:44); a handkerchief with motion blur and super slow motion (0:47); an hourglass (0:50):
These shots show the classical application of optical flow – slow motion. However, with our new technology we have been able to achieve extremely smooth pictures with virtually no artifacts, equivalent of a shutter speed at 1000 fps. At the same time, artificial motion blur equivalent of a shutter of far more than 360 degrees can be added to achieve a distinct “stroby” look, if desired, while maintaining very fluent motion in all cases. We are also able to speed up or slow down parts of the scene, e.g. to play the background in slow-motion while the foreground runs at normal speed. All of these effects can be applied on a per-pixel basis, thus giving full freedom to the artist.

Additional info on the film:

“Lucid Dreams Of Gabriel” is a surrealistic and non-linear story about a mother achieving immortality through her son, unconditional love, and the fluidity of time.

Producer: Markus Gross
DOP: Marco Barberi
Script & Director: Sasha A. Schriber
Camera & lenses: Arri Alexa XT with Zeiss prime lenses
Original language: English
Length: 11 minutes