An important task in object recognition is to enable algorithms to categorize objects under arbitrary poses in a cluttered 3D world. A recent paper by Savarese & Fei-Fei [1] has proposed a novel representation to model 3D object classes. In this representation stable parts of objects from one class are linked together to capture both the appearance and shape properties of the object class. We p...

We show an experiment on the generalization capability for arbitrary transformations. Although we have trained the network with 17 discrete transformations in the range [20,340] with 20-degree increments, our trained network can synthesize arbitrary view points with linear interpolations of one-hot vectors. For example, if [0,1,0,0,...0] and [0,0,1,0,...0] represent 40 and 60-degree transformat...

We propose a new depth-based representation of 3-D scenes primarily for the problem of arbitrary view synthesis. The information contained in a given image sequence is com-pacted into a single multivalued array, where points are organized by occlusions rather than by coherent aane motions. This grouping facilitates an automatic process to determine the number of layers and helps to reduce the a...

The purpose of this paper is to examine some aspects of unit selection for Text to Speech synthesis (TTS). We use Unit Selection as described in [2],[3]. The approach taken was to synthesize a large number of sentences and capture information about the selected units. We used approximately 25 million phonemes resulting from 10,000 les of AP newswire text. Given these statistics we looked at the...

Figure 1: Conceptual sketches of some three-dimensional (3D) medical telepresence paradigms. Left: a portable multi-camera unit. Right: hospital-based 3D viewing. (Sketches by Andrei State.)

We present a novel method for caricature synthesis based on mean value coordinates (MVC). Our method can be applied to any single frontal face image to learn a specified caricature face pair for frontal and 3D caricature synthesis. This technique only requires one or a small number of exemplar pairs and a natural frontal face image training set, while the system can transfer the style of the ex...

This contribution describes a system for 3D surface reconstruction and novel view synthesis from image streams of an unknown but static scene. The system operates fully automatic and estimates camera pose and 3D scene geometry using Structure-from-Motion and dense multi-camera stereo reconstruction. From these estimates, novel views of the scene can be rendered at interactive rates.

In this paper, we present a method which combines imagebased visual hull and human body part segmentation for overcoming the inability of the visual hull method to reconstruct concave regions. The virtual silhouette image corresponding to the given viewing direction is first produced with image-based visual hull. Human body part localization technique is used to segment the input images and the...

The context of this study is 3D video. Starting from multiview video plus depth as input data, the goal of the proposed representation based on 3D polygons is to take into account in a unified manner different issues such as compactness, compression, and intermediate view synthesis. The method used to build such a representation is divided into two parts. First, a set of 3D polygons is obtained...

We present a facial view synthesis technique based on explicit shape and reflectance information extracted from a single image. The technique combines an image based reflectance estimation process with a novel method of interpolating between needle-maps recovered using shape from shading. This allows images of a face to be synthesised under novel lighting, pose and skin reflectance given only o...