We introduce Pic2Tac, a novel system that automatically converts photographs into tactile images. It offers an alternative way to communicate visual information that is difficult to express using braille or alternative text. Current methods for creating tactile images are either limited in representation, or require handmade artefacts. Pic2Tac employs a unique approach that avoids a literal representation of image content (e.g. contours). Instead, it detects salient semantic content within photographs and translates them into tactile images using dedicated ‘tactile words’. Foreground objects are represented using icons, and patterns are used for background regions. The resulting binary image is printed on swell paper, where black regions rise to form a tactile image. Studies involving 60 participants, both sighted and with visual impairments, demonstrate the effectiveness of these tactile images in communicating semantic meaning. Our findings show that tactile and visual descriptions of scenes matched significantly. Overall, Pic2Tac is an affordable way to create accessible tactile images, costing only 1.50 USD per sheet.

Real-world paintings are made, by artists, using brush strokes as the rendering primitive to depict semantic content. The bulk of the Neural Style Transfer (NST) is known transferring style using texture patches, not strokes. The output looks like the content image, but some are traced over using the style texture: it does not look painterly. We adopt a very different approach that uses strokes. Our contribution is to analyse paintings to learn stroke families-that is, distributions of strokes based on their shape (a dot, straight lines, curved arcs, etc.). When synthesising a new output, these distributions are sampled to ensure the output is painted with the correct style of stroke. Consequently, our output looks more "painterly" than NST output based on texture. Furthermore, where strokes are placed is an important contributing factor in determining output quality, and we have also addressed this aspect. Humans place strokes to emphasize salient semantically meaningful image content. Conventional NST uses a content loss premised on filter responses that is agnostic to salience. We show that replacing that loss with one based on the language-image model benefits the output through greater emphasis of salient content.

Research has shown that convolutional neural networks for object recognition are vulnerable to changes in depiction because learning is biased towards the low-level statistics of texture patches. Recent works concentrate on improving robustness by applying style transfer to training examples to mitigate against over-fitting to one depiction style. These new approaches improve performance, but they ignore the geometric variations in object shape that real art exhibits: artists deform and warp objects for artistic effect. Motivated by this observation, we propose a method to reduce bias by jointly increasing the texture and geometry diversities of the training data. In effect, we extend the visual object class to include examples with shape changes that artists use. Specifically, we learn the distribution of warps that cover each given object class. Together with augmenting textures based on a broad distribution of styles, we show by experiments that our method improves performance on several cross-domain benchmarks.

Since its inception in 2015, Style Transfer has focused on texturing a content image using an art exemplar. Recently, the geometric changes that artists make have been acknowledged as an important component of style[42], [55], [62], [63]. Our contribution is to propose a neural network that, uniquely, learns a mapping from a 4D array of inter-feature distances to a non-parametric 2D warp field. The system is generic in not being limited by semantic class, a single learned model will suffice; all examples in this paper are output from one model.Our approach combines the benefits of the high speed of Liu et al. [42] with the non-parametric warping of Kim et al. [55]. Furthermore, our system extends the normal NST paradigm: although it can be used with a single exemplar, we also allow two style exemplars: one for texture and another geometry. This supports far greater flexibility in use cases than single exemplars can provide.

Visual camera localization using offline maps is widespread in robotics and mobile applications. Most state-of-the-art localization approaches assume static scenes, so maps are often reconstructed once and then kept constant. However, many scenes are dynamic and as changes in the scene happen, future localization attempts may struggle or fail entirely. Therefore, it is important for successful long-term localization to update and maintain maps as new observations of the scene, and changes in it, arrive. We propose a novel method for automatically discovering which points in a map remain stable over time, and which are due to transient changes. To this end, we calculate a stability store for each point based on its visibility over time, weighted by an exponential decay over time. This allows us to consider the impact of time when scoring points, and to distinguish which points are useful for long-term localization. We evaluate our method on the CMU Extended Seasons dataset (outdoors) and a new indoor dataset of a retail shop, and show the benefit of maintaining a `live map' that integrates updates over time using our exponential decay based method over a static `base map'.

We propose a novel problem revolving around two tasks: (i) given a scene, recommend objects to insert, and (ii) given an object category, retrieve suitable background scenes. A bounding box for the inserted object is predicted in both tasks, which helps downstream applications such as semiautomated advertising and video composition. The major challenge lies in the fact that the target object is neither present nor localized in the input, and furthermore, available datasets only provide scenes with existing objects. To tackle this problem, we build an unsupervised algorithm based on object-level contexts, which explicitly models the joint probability distribution of object categories and bounding boxes using a Gaussian mixture model. Experiments on our own annotated test set demonstrate that our system outperforms existing baselines on all sub-tasks, and does so using a unified framework. Future extensions and applications are suggested.

Example-guided image synthesis aims to synthesize an image from a semantic label map and an exemplary image indicating style. We use the term "style" in this problem to refer to implicit characteristics of images, for example: in portraits "style" includes gender, racial identity, age, hairstyle; in full body pictures it includes clothing; in street scenes it refers to weather and time of day and such like. A semantic label map in these cases indicates facial expression, full body pose, or scene segmentation. We propose a solution to the example-guided image synthesis problem using conditional generative adversarial networks with style consistency. Our key contributions are (i) a novel style consistency discriminator to determine whether a pair of images are consistent in style; (ii) an adaptive semantic consistency loss; and (iii) a training data sampling strategy, for synthesizing style-consistent results to the exemplar. We demonstrate the efficiency of our method on face, dance and street view synthesis tasks.

Detecting small objects is a challenging task. We focus on a special case: the detection and classification of traffic signals in street views. We present a novel framework that utilizes a visual attention model to make detection more efficient, without loss of accuracy, and which generalizes. The attention model is designed to generate a small set of candidate regions at a suitable scale so that small targets can be better located and classified. In order to evaluate our method in the context of traffic signal detection, we have built a traffic light benchmark with over 15,000 traffic light instances, based on Tencent street view panoramas. We have tested our method both on the dataset we have built and the Tsinghua-Tencent 100K (TT100K) traffic sign benchmark. Experiments show that our method has superior detection performance and is quicker than the general faster RCNN object detection framework on both datasets. It is competitive with state-of-the-art specialist traffic sign detectors on TT100K, but is an order of magnitude faster. To show generality, we tested it on the LISA dataset without tuning, and obtained an average precision in excess of 90%.

We present a fast, novel image-based technique for reverse engineering woven fabrics at a yarn level. These models can be used in a wide range of interior design and visual special effects applications. To recover our pseudo-Bidirectional Texture Function (BTF), we estimate the three-dimensional (3D) structure and a set of yarn parameters (e.g., yarn width, yarn crossovers) from spatial and frequency domain cues. Drawing inspiration from previous work [Zhao et al. 2012], we solve for the woven fabric pattern and from this build a dataset. In contrast, however, we use a combination of image space analysis and frequency domain analysis, and, in challenging cases, match image statistics with those from previously captured known patterns. Our method determines, from a single digital image, captured with a digital single-lens reflex (DSLR) camera under controlled uniform lighting, the woven cloth structure, depth, and albedo, thus removing the need for separately measured depth data. The focus of this work is on the rapid acquisition of woven cloth structure and therefore we use standard approaches to render the results. Our pipeline first estimates the weave pattern, yarn characteristics, and noise statistics using a novel combination of low-level image processing and Fourier analysis. Next, we estimate a 3D structure for the fabric sample using a first-order Markov chain and our estimated noise model as input, also deriving a depth map and an albedo. Our volumetric textile model includes information about the 3D path of the center of the yarns, their variable width, and hence the volume occupied by the yarns, and colors. We demonstrate the efficacy of our approach through comparison images of test scenes rendered using (a) the original photograph, (b) the segmented image, (c) the estimated weave pattern, and (d) the rendered result.

Quadrics are a compact mathematical formulation for a range of primitive surfaces. A problem arises when there are not enough data points to compute the model but knowledge of the shape is available. This paper presents a method for fitting a quadric with a Bayesian prior. We use a matrix normal prior in order to favour ellipsoids when fitting to ambiguous data. The results show the algorithm copes well when there are few points in the point cloud, competing with contemporary techniques in the area.

This paper addresses the segmentation of videos with arbitrary motion, including dynamic textures, using novel motion features and a supervised learning approach. Dynamic textures are commonplace in natural scenes, and exhibit complex patterns of appearance and motion (e.g. water, smoke, swaying foliage). These are difficult for existing segmentation algorithms, often violate the brightness constancy assumption needed for optical flow, and have complex segment characteristics beyond uniform appearance or motion. Our solution uses custom spatiotemporal filters that capture texture and motion cues, along with a novel metric-learning framework that optimizes this representation for specific objects and scenes. This is used within a hierarchical, graph-based segmentation setting, yielding state-of-the-art results for dynamic texture segmentation. We also demonstrate the applicability of our approach to general object and motion segmentation, showing significant improvements over unsupervised segmentation and results comparable to the best task specific approaches.

We present a Bayesian approach to tactile object recognition that improves on state-of-the-art in using single-touch events in two ways. First by improving recognition accuracy from about 90% to about 95%, using about half the number of touches. Second by reducing the number of touches needed for training from about 200 to about 60. In addition, we use a new tactile sensor that is less than one tenth of the cost of widely available sensors. The paper describes the sensor, the likelihood function used with the Naive Bayes classifier, and experiments on a set of ten real objects. We also provide preliminary results to test our approach for its ability to generalise to previously unencountered objects.

Cross-depiction is the recognition—and synthesis—of objects whether they are photographed, painted, drawn, etc. It is a significant yet underresearched problem. Emulating the remarkable human ability to recognise and depict objects in an astonishingly wide variety of depictive forms is likely to advance both the foundations and the applications of computer vision. In this paper we motivate the cross-depiction problem, explain why it is difficult, and discuss some current approaches. Our main conclusions are (i) appearance-based recognition systems tend to be over-fitted to one depiction, (ii) models that explicitly encode spatial relations between parts are more robust, and (iii) recognition and non-photorealistic synthesis are related tasks.

This paper provides evidence that about half of all the regions in segmented images can be classified as one a few simple shapes. Using three segmentation algorithms, three different image databases, and two shape descriptors, we empirically show that shapes such as triangles, squares, and circles are observed, up to an affine transform and at a much higher rate than random shapes. This result has potential value in applications such as scene understanding, visual object classification, and matching because qualitative shapes can be used as features. We show an application in scene categorisation based on what might be called ‘bag of shapes’ .

We introduce a video-based approach for producing water surface models. Recent advances in this field output high-quality results but require dedicated capturing devices and only work in limited conditions. In contrast, our method achieves a good tradeoff between the visual quality and the production cost: It automatically produces a visually plausible animation using a single viewpoint video as the input. Our approach is based on two discoveries: first, shape from shading (SFS) is adequate to capture the appearance and dynamic behavior of the example water; second, shallow water model can be used to estimate a velocity field that produces complex surface dynamics. We will provide qualitative evaluation of our method and demonstrate its good performance across a wide range of scenes.

This paper shows that classifying shapes is a tool useful in nonphotorealistic rendering (NPR) from photographs. Our classifier inputs regions from an image segmentation hierarchy and outputs the "best" fitting simple shape such as a circle, square, or triangle. Other approaches to NPR have recognized the benefits of segmentation, but none have classified the shape of segments. By doing so, we can create artwork of a more abstract nature, emulating the style of modern artists such as Matisse and other artists who favored shape simplification in their artwork. The classifier chooses the shape that "best" represents the region. Since the classifier is trained by a user, the "best shape" has a subjective quality that can over-ride measurements such as minimum error and more importantly captures user preferences. Once trained, the system is fully automatic, although simple user interaction is also possible to allow for differences in individual tastes. A gallery of results shows how this classifier contributes to NPR from images by producing abstract artwork.

We are interested in matching objects in photographs, paintings, sketches and so on; after all, humans have a remarkable ability to recognise objects in images, no matter how they are depicted. We conduct experiments in matching, and conclude that the key to robustness lies in object description. The existing literature consists of numerous feature descriptors that rely heavily on photometric properties such as colour and illumination to describe objects. Although these methods achieve high rates of accuracy in applications such as detection and retrieval of photographs, they fail to generalise datasets consisting of mixed depictions. Here, we propose a more general approach for describing objects invariant to depictive style. We use structure at a global level, which is combined with simple non-photometric descriptors at a local level. There is no need for any prior learning. Our descriptor achieves results on par with existing state of the art, when applied to object matching on a standard dataset consisting of photographs alone and outperforms the state of the art when applied to depiction-invariant object matching.

This paper provides evidence that about half of all the regions in segmented images can be classified as one a few simple shapes. Using three segmentation algorithms, three different image databases, and two shape descriptors, we empirically show that shapes such as triangles, squares, and circles are observed, up to an affine transform and at a much higher rate than random shapes. This result has potential value in applications such as scene understanding, visual object classification, and matching because qualitative shapes can be used as features. We show an application in scene categorisation based on what might be called ‘bag of shapes’ .

Finding meaningful groupings of image primitives has been a long-standing problem in computer vision. This paper studies how salient groupings can be produced using established theories in the field of visual perception alone. The major contribution is a novel definition of the Gestalt principle of Prägnanz, based upon Koffka's definition that image descriptions should be both stable and simple. Our method is global in the sense that it operates over all primitives in an image at once. It works regardless of the type of image primitives and is generally independent of image properties such as intensity, color, and texture. A novel experiment is designed to quantitatively evaluate the groupings outputs by our method, which takes human disagreement into account and is generic to outputs of any grouper. We also demonstrate the value of our method in an image segmentation application and quantitatively show that segmentations deliver promising results when benchmarked using the Berkeley Segmentation Dataset (BSDS).

We present a probabilistic approach for the automatic production of tree models with convincing 3D appearance and motion. The only input is a video of a moving tree that provides us an initial dynamic tree model, which is used to generate new individual trees of the same type. Our approach combines global and local constraints to construct a dynamic 3D tree model from a 2D skeleton. Our modeling takes into account factors such as the shape of branches, the overall shape of the tree, and physically plausible motion. Furthermore, we provide a generative model that creates multiple trees in 3D, given a single example model. This means that users no longer have to make each tree individually, or specify rules to make new trees. Results with different species are presented and compared to both reference input data and state of the art alternatives.

This paper introduces a new statistical method for combining vision and robot dynamics to generate trajectories to intercept a moving object. Previous methods only use information from the kinematics without considering the forces needed to move along the trajectory. Using robot dynamics allows extra measures, such as energy efficiency, to be optimised alongside maximising the likelihood of intercepting the target. We derive a statistical model for a vision system and a Lagrangian dynamical model of a robotic arm, showing how to relate joint torques to the vision. The method is tested by applying it to the problem of catching a simulated moving object.

Active Appearance Models (AAM) are a useful and popular tool for modelling facial variations. They have been used in face tracking, recognition and synthesis applications. For modelling facial dynamics of speech, they have been used in conjunction with Hid-den Markov Models (HMM). However, the high dimensionality of the training data and of the resulting AAMs leads to long learning time of HMMs and thus imposes serious limitations on their joint use. Here, we propose a new method for learning HMMs of facial dynamics incremen-tally. Our algorithm is fully unsupervised and can be used for on-line learning as new data becomes available. Another important feature of our algorithm is the automatic choice of the number of states in the model. We show in experiments an improvement in learning speed of three orders of magnitude. Finally, we demonstrate the quality of the learned HMMs by generating video footage of a talking face. 1 Introduction and

This paper is about shape fitting to regions that segment an image and some applications that rely on the abstraction that offers. The novelty lies in three areas: (1) we fit a shape drawn from a selection of shape families, not just one class of shape, using a supervised classifier; (2) We use results from the classifier to match photographs and artwork of particular objects using a few qualitative shapes, which overcomes the significant differences between photographs and paintings; (3) We further use the shape classifier to process photographs into abstract synthetic art which, so far as we know, is novel too. Thus we use our shape classier in both discriminative (matching) and generative (image synthesis) tasks. We conclude the level of abstraction offered by our shape classifier is novel and useful. 1

We are interested in descriptors for dynamic textures that supports both further analysis and resynthesis applications. These tasks demand that the description encodes appearance and motion separably. This paper shows that a tree hierarchy which is built from nested image regions can be acquired via analysis of the first few frames of a video sequence. The tree is stable over space and time and leads to a measurably improved performance on the generic application of tracking the dynamic texture itself. The claim is supported by experimental data taken from a range of dynamic textures including trees and flowers. We conclude that both appearance and motion are better described using the stable structure rather than by a sequence of equivalent hierarchies each optimised for a single frame, because motion data helps to reduce clutter artefacts from trees built for static images. 1

Colour constancy is the problem of mapping colours in a scene as the lighting environment changes. This problem has been studied for many years, and linear solutions that give excellent results are available for Lambertian scenes. More complex reflective environments demand non-linear transforms, but the models are harder to fit and in some cases bring worse results due to over-fitting. We introduce a fully non-linear colour constancy model and a method to select an optimal model from amongst a family of discrete models, including linear models. Once given a set of colour matches our model selection is fully automatic. The selection method is experimentally verified, and is put to use in two applications: scene re-lighting and environment mapping. 1

The problem of identifying the class of an object from its visual appearance has received significant attention recently. Most of the work to date is premised on photometric measures, often building codebooks made from interest regions. All of it has been tested only on photographs, so far as we know. Our approach differs in two significant ways. First, we do not build a codebook of interest regions but instead make use of a hierarchical description of an image based on a watershed transform. Root nodes in the hierarchy are putative objects to be classified. Second, we classify these putative objects using a vector of fixed length that represents the structure of the hierarchy below the node. This allows us to classify not just photographs, but also paintings and drawings of visual objects. 1

Abstract-We introduce a simple but versatile camera model that we call the Rational Tensor Camera (RTcam). RTcams are well principled mathematically and provably subsume several important contemporary camera models in both computer graphics and vision; their generality is one contribution. They can be used alone or compounded to produce more complicated visual effects. In this paper, we apply RTcams to generate synthetic artwork with novel perspective effects from real photographs. Existing Nonphotorealistic Rendering from Photographs (NPRP) is constrained to the projection inherent in the source photograph, which is most often linear. RTcams lift this restriction and so contribute to NPRP via multiperspective projection. This paper describes RTcams, compares them to contemporary alternatives, and discusses how to control them in practice. Illustrative examples are provided throughout.

This paper demonstrates how to determine canonical views of objects in a way that is simple, robust and versatile. Common parlance loosely defines canonical views as the “front”, “side”, and “top” views of an object. Our approach determines these views for objects whether represented by images or three-dimensional points; neither image segmentation nor model analysis is required. It is easy to introduce constraints so that other views can be determined, as desired. We explain our method and compare it qualitatively to alternatives.

The contribution of this paper is a novel framework for synthesizing nonphotorealistic animations from real video sequences. We demonstrate that, through automated mid-level analysis of the video sequence as a spatiotemporal volume--a block of frames with time as the third dimension--we are able to generate animations in a wide variety of artistic styles, exhibiting a uniquely high degree of temporal coherence. In addition to rotoscoping, matting, and novel temporal effects unique to our method, we demonstrate the extension of static nonphotorealistic rendering (NPR) styles to video, including painterly, sketchy, and cartoon shading. We demonstrate how this novel coherent shading framework may be combined with our earlier motion emphasis work to produce a comprehensive "Video Paintbox" capable of rendering complete cartoon-styled animations from video clips.

The contribution of this paper is a novel spatiotemporal description of real video sequences. Our description comprises a set of surfaces that separate objects in the video, and an accompanying database which describes objects in the video. We explain how to automatically process video into our description, and use it to solve a long-standing problem in Computer Graphics; that of automatically producing non-photorealistic (NPR) animations from video sequences. We show empirically that our description is highly compact relative to alternative coding schemes, and that our NPR animation technique out performs the current state-of-the-art in automatic video painting by about an order of magnitude, in terms of temporal coherence. 1

We introduce a method to detect low-level features that is prescriptive (as Canny edge-detection is) but trained by a user. The user simply chooses feature classes and points to class instances. Given a input image, we compute a probability map that indicates how likely it is to belong to each of the userdefined classes; so combining different kinds of feature detector into a single, user-trainable system. This paper explains how we characterise features, how we train and detect, and gives an algorithm that automatically determines feature scale. We empirically compare the method to standard edge and corner detectors, showing a measurable advantage in each case.

In recent years the Vision community has shown interest in processing images and video for use by the entertainment industries. Typical applications include 3D reconstruction of models, and rendering graphics models into video. This paper broadly aligns with that trend, but differs in that we process video to emphasise motion in Cartoon-like styles, in which moving objects deform in defiance of physical laws, and leave trailing marks of one kind or another in their wake. We provide an introduction to the effects real animators use, and show how a judicious choice of standard processing techniques, supplemented by novel methods, can be used to achieve convincing results. We illustrate the robustness of our method using several video sequences, ranging in content from simple oscillatory to articulated motion, under both static and moving camera conditions.

In this paper we present a method for adding Hidden Markov Models. The main advantages of our method are that it does not require the data the models had been trained on, allows a change in the number of components, does not assume independence of the components to be added and is resistant to the order in which the training data arrives. We assessed the method in the experiments with synthetic data, which showed good accuracy. Finally, we present an application in computer vision. 1

The contribution of the paper is a novel nonphotorealistic rendering (NPR) technique, influenced by the style of Cubist art. Specifically, we are motivated by artists such as Picasso and Braque, who produced art work by composing elements of a scene taken from multiple points of view; paradoxically, such compositions convey a sense of motion without assuming temporal dependence between views. Our method accepts a set of two-dimensional images as input and produces a Cubist style painting with minimal user interaction. We use salient features identified within the image set, such as eyes, noses, and mouths, as compositional elements; we believe the use of such features to be a unique contribution to NPR. Before composing features into a final image, we geometrically distort them to produce the more angular forms common in Cubist art. Finally, we render the composition to give a painterly effect, using an automatic algorithm. This paper describes our method, illustrating the application of our algorithm with a gallery of images. We conclude with a critical appraisal and suggest the use of "high-level" features is of interest to NPR.

We propose a novel hierarchical model of human dynamics for view independent tracking of the human body in monocular video sequences. The model is trained using real data from a collection of people. Kinematics are encoded using Hierarchical Principal Component Analysis, and dynamics are encoded using Hidden Markov Models. The top of the hierarchy contains information about the whole body. The lower levels of the hierarchy contain more detailed information about possible poses of some subpart of the body. When tracking, the lower levels of the hierarchy are shown to improve accuracy. In this article we describe our model and present experiments that show we can recover 3D skeletons from 2D images in a view independent manner, and also track people the system was not trained on.

We present new deterministic methods that, given two eigenspace models-each representing a set of n-dimensional observations-will: 1) merge the models to yield a representation of the union of the sets and 2) split one model from another to represent the difference between the sets. As this is done, we accurately keep track of the mean. Here, we give a theoretical derivation of the methods, empirical results relating to the efficiency and accuracy of the techniques, and three general applications, including the construction of Gaussian mixture models that are dynamically updateable.

This paper provides two algorithms; one for adding eigenspaces, another for subtracting them, thus allowing for incremental updating and downdat-ing of data models. Importantly, and unlike previous work, we keep an ac-curate track of the mean of the data, which allows our methods to be used in classification applications. The result of adding eigenspaces, each made from a set of data, is an approximation to that which would obtain were the sets of data taken together. Subtracting eigenspaces yields a result approximating that which would obtain were a subset of data used. Using our algorithms it is possible to perform “arithmetic ” on eigenspaces without reference to the orig-inal data. We illustrate the use of our algorithms in three generic applications, including the dynamic construction of Gaussian mixture models. 1

We present Q‐mapping which is a technique for rendering three‐dimensional objects using nonphotorealistic cues, by applying Q‐maps. Q‐maps are three‐dimensional textures that make marks on objects, and thus provide visual cues for shape, shade, and texture. Q‐maps adapt to light intensity, typically by making more marks in darker areas. Q‐maps can produce images with a very wide range of visual styles (e.g. half tone shading, and pen‐and‐ink colour wash). The primary contribution is that these styles reside in a single parametric space. Importantly this space includes photorealism as a style, which is therefore regarded as a special case of nonphotorealistic image rendering in general. We illustrate our explanation of Q‐mapping using examples from scientific visualisation and computer graphics – and provide a gallery of images to show the versatility of the approach.

Eigenspace models are a convenientway to represent sets of observations with widespread applications, including classi#cation. In this paper we describe a new constructive method for incrementally adding observations to an eigenspace model. Our contribution is to explicitly account forachange in origin as well as a change in the number of eigenvectors needed in the basis set. No other method wehave seen considers change of origin, yet both are needed if an eigenspace model is to be used for classi#cation purposes. We empirically compare our incremental method with two alternatives from the literature and show our method is the more useful for classi#cation because it computes the smaller eigenspace model representing the observations. 1 Introduction The contribution of this paper is a method for incrementally computing eigenspace models in the context of using them for classi#cation. Eigenspace models are widely used in computer vision. Applications include: face recognition #8# where...

Reconstructing vasculature in three dimensions is a challenging problem. Early approaches concentrated on coronary vasculature in X-ray images, recent work uses magnetic resonance imagery of cerebral vasculature. In both cases a priori information has been used, and often the way this is represented has proven limiting to the scope of applications supported. For example, a particular representation may be useful only for X-ray images. This paper addresses two issues: 1) representing a collection of vasculature and 2) the reconstruction of individual vasculature from images. Our representation learns the variations in branching structures and vessel shapes that occur between individuals. It supports a vascular catalogue containing three-dimensional (3-D) anatomical models. The representation is task independent; here we use it to reconstruct vasculature from images. Our algorithm has four features to which we draw attention: 1) it is not premised wholly upon X-ray images (though that is our focus here); 2) it produces several feasible solutions rather than one; 3) it can generalize from the catalogue to reconstruct instances not yet learned; 4) it exhibits polynomial time complexity, reasonable memory consumption, and is reliable. Both our representation and reconstruction algorithm are new and useful approaches. In support of these claims, we present results gathered from X-rays of both simulated and real vasculature.