Disney Research Studios

In this paper we propose a method for dynamic rescaling of music, inspired by recent works on image retargeting, video reshuffling and character animation in the computer graphics community. Given the desired target length of a piece of music and optional additional constraints such as position and importance of certain parts, we build on concepts from seam carving, video textures and motion graphs and extend them to allow for a global optimization of jumps in an audio signal.

We describe in detail the required components, decisions, and new techniques that together make a usable, interactive tool for compositing HD video, paying special attention to running time and performance of each section.

In this paper, we propose a novel method to compress video content based on image retargeting. First, a saliency map is extracted from the video frames either automatically or according to user input.

We present a theoretical analysis of error of many combinations of Monte Carlo estimators used in image synthesis.

We present a solution for generating high-quality stereo panoramas at megapixel resolutions.

This paper provides measurement and fitting methods that allow nonlinear models to be fit to the observed deformation of a particular cloth sample.

This project presents a finer scale technique to demonstrate for the first time the processing of densely leafed foliage – computation of 3D structure, plus extraction of statistics for leaf shape and the configuration of neighboring leaves.

We present a method for consistent automatic transfer of edits applied to one image to many other images of the same object or scene.

In this project, we developed a model of internal friction based on a reparameterization of Dahl’s model and validated that this model provides a good match to important features of cloth hysteresis even with a minimal set of parameters.

We present a technique for adding fine-scale details and expressiveness to low-resolution art-directed facial performances, such as those created manually using a rig, via marker-based capture, by fitting a morphable model to a video, or through Kinect reconstruction using recent faceshift technology.