Graphics and Vision

A Topological Approach to Hierarchical Segmentation Using Mean Shift
Mean shift is a popular method to segment images and videos. Pixels are represented by feature points, and the segmentation is driven by the point density in feature space. In this paper, we introduce the use of Morse theory to interpret mean shift as a topological decomposition of the feature space into density modes. This allows us to build on the watershed technique and design a new algorithm to compute mean-shift segmentations of images and videos. In addition, we introduce the use of topological persistence to create a segmentation hierarchy. We validated our method by clustering images using color cues. In this context, our technique runs faster than previous work, especially on videos and large images.

Two-scale Tone Management for Photographic Look
We introduce a new approach to tone management for photographs. Whereas traditional tone-mapping operators target a neutral and faithful rendition of the input image, we explore pictorial looks by controlling visual qualities such as the tonal balance and the amount of detail. Our method is based on a two-scale non-linear decomposition of an image. We modify the different layers based on their histograms and introduce a technique that controls the spatial variation of detail. We introduce a Poisson correction that prevents potential gradient reversal and preserves detail. In addition to directly controlling the parameters, the user can transfer the look of a model photograph to the picture being edited.

Inverse Kinematics for Reduced Deformable Models
Articulated shapes are aptly described by reduced deformable models that express required shape deformations using a compact set of control parameters. Although sufficient to describe most shape deformations, these control parameters can be ill-suited for animation tasks, particularly when reduced deformable models are inferred automatically from example shapes.

Interactive Animation of Dynamic Manipulation
Lifelike animation of object manipulation requires dynamic interaction between animated characters, objects, and their environment. These interactions can be animated automatically with physically based simulations but proper controls are needed to animate characters that move realistically and that accomplish tasks in spite of unexpected disturbances. This paper describes an effcient control algorithm that generates realistic animations by incorporating motion data into task execution. The end result is a versatile system for interactive animation of dynamic manipulation tasks such as lifting, catching, and throwing.

Face Transfer with Multilinear Models
Face Transfer is a method for mapping videorecorded performances of one individual to facial animations of another. It extracts visemes (speech-related mouth articulations), expressions, and three-dimensional (3D) pose from monocular video or film footage. These parameters are then used to generate and drive a detailed 3D textured face mesh for a target identity, which can be seamlessly rendered back into target footage. The underlying face model automatically adjusts for how the target performs facial expressions and visemes. The performance data can be easily edited to change the visemes, expressions, pose, or even the identity of the target—the attributes are separably controllable.

Continuous Capture of Skin Deformation
We describe a method for the acquisition of deformable human geometry from silhouettes. Our technique uses a commercial tracking system to determine the motion of the skeleton, then estimates geometry for each bone using constraints provided by the silhouettes from one or more cameras. These silhouettes do not give a complete characterization of the geometry for a particular point in time, but when the subject moves, many observations of the same local geometries allow the construction of a complete model. Our reconstruction algorithm provides a simple mechanism for solving the problems of view aggregation, occlusion handling, hole filling, noise removal, and deformation modeling. The resulting model is parameterized to synthesize geometry for new poses of the skeleton.

Style Translation for Human Motion
Style translation is the process of transforming an input motion into a new style while preserving its original content. This problem is motivated by the needs of interactive applications, which require rapid processing of captured performances. Our solution learns to translate by analyzing differences between performances of the same content in input and output styles. It relies on a novel correspondence algorithm to align motions, and a linear time-invariant model to represent stylistic differences. Once the model is estimated with system identification, our system is capable of translating streaming input with simple linear operations at each frame.

Example-Based Control of Human Motion
In human motion control applications, the mapping between a control specification and an appropriate target motion often defies an explicit encoding. We present a method that allows such a mapping to be defined by example, given that the control specification is recorded motion. Our method begins by building a database of semantically meaningful instances of the mapping, each of which is represented by synchronized segments of control and target motion. A dynamic programming algorithm can then be used to interpret an input control specification in terms of mapping instances. This interpretation induces a sequence of target segments from the database, which is concatenated to create the appropriate target motion. We evaluate our method on two examples of indirect control.

Texture Transfer Using Geometric Correlation
Texture variation on real-world objects often correlates with underlying geometric characteristics and creates a visually rich appearance. We present a technique to transfer such geometry-dependent texture variation from an example textured model to new geometry in a visually consistent way. It captures the correlation between a set of geometric features, such as curvature, and the observed diffuse texture. We perform dimensionality reduction on the overcomplete feature set which yields a compact guidance field that is used to drive a spatially varying texture synthesis model. In addition, we introduce a method to enrich the guidance field when the target geometry strongly differs from the example.