A general paradigm f o r recognizing 3 0 objects is offered, and applied to some geometric primit... more A general paradigm f o r recognizing 3 0 objects is offered, and applied to some geometric primitives (spheres, cylinders, cones, and tori). The assumption is that a curve on the surface was measured with high accuracy (for instame, by a sensory robot). Differential invariants of thte curve in one method and differential properties of curves and surfaces in the other are then used to recognize the surface. The motivation is twofold: the output of some devices is not surface range data, but such curves. So, surface invariants, which may be simpier in some cases, cannot always be obtained. Also, (a considerable speedup is obtained by using curve data, as opposed to surface data which usually contains a much higher number of points.
; I general paradigm for recognizing 3D objects is offered, and applied to some geometric primiti... more ; I general paradigm for recognizing 3D objects is offered, and applied to some geometric primitives [sphe,res, cylinders, cones, and tori). The assumption is that Q curve on the surface W Q S measured with high accuracy (for instance, by a sensory robot). Differential properties of curves and surfaces are used to recognize the surface. The motivation is t,wofold: the output of some devices is not surface range data, but such curves. So, surface invariants, which may be simpler in some cases, cannot Q~W Q Y S be obtained. Also, a consaderable speedup is obtained by using curve data, QS opposed to surface data which usually contains Q much higher number of points.
Ayellet Tal Technion, Israel (a) Input image (b) Classification by shape (c) Classification by pe... more Ayellet Tal Technion, Israel (a) Input image (b) Classification by shape (c) Classification by period (d) Generation Figure 1. Analyzing archaeological artifacts. Images of archaeological artifacts are extremely challenging to analyze, since they are eroded, broken and stained (a). Our model manages to classify these artifacts not only by shape (b), but also by historical period (c). In this figure, each ellipse bounds artifacts from the same class, demonstrating the great diversity within a class. Furthermore, our model generates a drawing of the given artifact (d), which is a standard way of archaeological documentation. The top row shows an Ibex dated to the Late Iron, whereas the bottom row shows a Lion dated to the Late Bronze.
Journal on computing and cultural heritage, Mar 1, 2013
This paper addresses the problem of automatic reconstruction of a 3D relief object from a line dr... more This paper addresses the problem of automatic reconstruction of a 3D relief object from a line drawing. Our main application is reconstruction of archaeological artifacts based on line drawings. The problem is challenging due to five reasons: the small number of orthogonal views of the object, the sparsity of the strokes, their ambiguity, their large number and their interrelations. We partition the reconstruction problem into two sub-problems. First, we reconstruct the underlying smooth base of the object from the silhouette. Assuming that the variation of bases belonging to the same class of objects is relatively small, we create the base by modifying a similar base retrieved from a database. Second, we reconstruct the relief on top of the base. Our approach is able to reconstruct the relief from a complex drawing that consists of many interrelated strokes. Rather than viewing the inter-dependencies as a problem, we show how they can be exploited to automatically generate a good initial interpretation of the line drawing. Even though our algorithm is generic, its strength is demonstrated by the reconstruction of artifacts from manual drawings taken from real archaeological reports. These drawings are highly challenging, since artists created very complex and detailed descriptions of artifacts regardless of any considerations concerning their future use for shape reconstruction.
We present a novel technique for creating realistic facial animations given a small number of rea... more We present a novel technique for creating realistic facial animations given a small number of real images and a few parameters for the in-between images. This scheme can also be used for reconstructing facial movies where the parameters can be automatically extracted from the images. The in-between images are produced without ever generating a three-dimensional model of the face. Since facial motion due to expressions are not well defined mathematically our approach is based on utilizing image patterns in facial motion. These patterns were revealed by an empirical study which analyzed and compared image motion patterns in facial expressions. The major contribution of this work is showing how parameterized "ideal" motion templates can generate facial movies for different people and different expressions, where the parameters are extracted automatically from the image sequence. To test the quality of the algorithm, image sequences (one of which was taken from a TV news broadcast) were reconstructed, yielding movies hardly distinguishable from the originals.
Presence: Teleoperators & Virtual Environments, Dec 1, 2004
This paper discusses the problem of inserting three-dimensional models into a single image. The m... more This paper discusses the problem of inserting three-dimensional models into a single image. The main focus of the paper is on the accurate recovery of the camera's parameters, so that 3D models can be inserted in the "correct" position and orientation. The paper addresses two issues. The first is an automatic extraction of the principal vanishing points from an image. The second is a theoretical and an experimental analysis of the errors. To test the concept, a system which "plants" virtual 3D objects in the image was implemented. It was tested on many indoor augmented reality scenes. Our analysis and experiments have shown that errors in the placement of the objects are un-noticeable.
Curves on objects can convey the inherent features of the shape. This paper defines a new class o... more Curves on objects can convey the inherent features of the shape. This paper defines a new class of view-independent curves, denoted demarcating curves. In a nutshell, demarcating curves are the loci of the "strongest" inflections on the surface. Due to their appealing capabilities to extract and emphasize 3D textures, they are applied to artifact illustration in archaeology, where they can serve as a worthy alternative to the expensive, time-consuming, and biased manual depiction currently used.
This paper addresses the problem of automatic reconstruction of a 3D relief from a line drawing o... more This paper addresses the problem of automatic reconstruction of a 3D relief from a line drawing on top of a given base object. Reconstruction is challenging due to four reasons-the sparsity of the strokes, their ambiguity, their large number, and their interrelations. Our approach is able to reconstruct a model from a complex drawing that consists of many interrelated strokes. Rather than viewing the interdependencies as a problem, we show how they can be exploited to automatically generate a good initial interpretation of the line drawing. Then, given a base and an interpretation, we propose an algorithm for reconstructing a consistent surface. The strength of our approach is demonstrated in the reconstruction of archaeological artifacts from drawings. These drawings are highly challenging, since artists created very complex and detailed descriptions of artifacts regardless of any considerations concerning their future use for shape reconstruction.
Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)
A general paradigm f o r recognizing 3 0 objects is offered, and applied to some geometric primit... more A general paradigm f o r recognizing 3 0 objects is offered, and applied to some geometric primitives (spheres, cylinders, cones, and tori). The assumption is that a curve on the surface was measured with high accuracy (for instame, by a sensory robot). Differential invariants of thte curve in one method and differential properties of curves and surfaces in the other are then used to recognize the surface. The motivation is twofold: the output of some devices is not surface range data, but such curves. So, surface invariants, which may be simpier in some cases, cannot always be obtained. Also, (a considerable speedup is obtained by using curve data, as opposed to surface data which usually contains a much higher number of points.
This state of the art report describes the techniques of shape analysis, and of metadata search t... more This state of the art report describes the techniques of shape analysis, and of metadata search that have been already implemented in cultural heritage or we think are useful for the GRAVITATE project. These fields are relatively disjoint, and the research and development challenge of GRAVITATE is precisely to merge them. After the review of the current literature on these fields, we end the report with common remarks on possible or plausible cross connections that suggest themselves. These considerations will be refined for the Roadmap for Research deliverable.
The GRAVITATE project is developing techniques that bring together geometric and semantic data an... more The GRAVITATE project is developing techniques that bring together geometric and semantic data analysis to provide a new and more effective method of re-associating, reassembling or reunifying cultural objects that have been broken or dispersed over time. The project is driven by the needs of archaeological institutes, and the techniques are exemplified by their application to a collection of several hundred 3D-scanned fragments of large-scale terracotta statues from Salamis, Cyprus. The integration of geometrical feature extraction and matching with semantic annotation and matching into a single decision support platform will lead to more accurate reconstructions of artefacts and greater insights into history. In this paper we describe the project and its objectives, then we describe the progress made to date towards achieving those objectives: describing the datasets, requirements and analysing the state of the art. We follow this with an overview of the architecture of the integr...
2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009
Edge detection in images has been a fundamental problem in computer vision from its early days. E... more Edge detection in images has been a fundamental problem in computer vision from its early days. Edge detection on surfaces, on the other hand, has received much less attention. The most common edges on surfaces are ridges and valleys, used for processing range images in computer vision, as well as for non-photorealistic rendering in computer graphics. We propose a new type of edges on surfaces, termed relief edges. Intuitively, the surface can be considered as an unknown smooth manifold, on top of which a local height image is placed. Relief edges are the edges of this local image. We show how to compute these edges from the local differential geometric surface properties, by fitting a local edge model to the surface. We also show how the underlying manifold and the local images can be roughly approximated and exploited in the edge detection process. Last but not least, we demonstrate the application of relief edges to artifact illustration in archaeology.
Proceedings IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems
We present a technique for reconstructing facial movies, given a small number of real images and ... more We present a technique for reconstructing facial movies, given a small number of real images and a few parameters for the in-between images. The parameters can be automatically extracted by a tracking system. This scheme can also be used for creating realistic facial animations and for compression of facial movies. The in-between images are produced without ever generating a 3D
Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)
; I general paradigm for recognizing 3D objects is offered, and applied to some geometric primiti... more ; I general paradigm for recognizing 3D objects is offered, and applied to some geometric primitives [sphe,res, cylinders, cones, and tori). The assumption is that Q curve on the surface W Q S measured with high accuracy (for instance, by a sensory robot). Differential properties of curves and surfaces are used to recognize the surface. The motivation is t,wofold: the output of some devices is not surface range data, but such curves. So, surface invariants, which may be simpler in some cases, cannot Q~W Q Y S be obtained. Also, a consaderable speedup is obtained by using curve data, QS opposed to surface data which usually contains Q much higher number of points.
Collision detection is a fundamental problem in computer graphics. In this paper, temporal cohere... more Collision detection is a fundamental problem in computer graphics. In this paper, temporal coherence is studied and an algorithm exploiting it for bounding volume hierarchies, is presented. We show that maintaining some of the intersection tests computed in the previous frame, along with certain information, is able to speedup the intersection tests considerably. The algorithm is able to accelerate the collision detection for small motions and works as fast as the regular algorithm for large motions, where temporal coherence does not exist. The algorithm framework can be implemented for any type of bounding volume hierarchy. To demonstrate this, it was implemented for the OBB and the AABB data structures and tested on several benchmark scenarios.
2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013
This paper extends to surfaces the multi-scale approach of edge detection on images. The common p... more This paper extends to surfaces the multi-scale approach of edge detection on images. The common practice for detecting curves on surfaces requires the user to first select the scale of the features, apply an appropriate smoothing, and detect the edges on the smoothed surface. This approach suffers from two drawbacks. First, it relies on a hidden assumption that all the features on the surface are of the same scale. Second, manual user intervention is required. In this paper, we propose a general framework for automatically detecting the optimal scale for each point on the surface. We smooth the surface at each point according to this optimal scale and run the curve detection algorithm on the resulting surface. Our multi-scale algorithm solves the two disadvantages of the single-scale approach mentioned above. We demonstrate how to realize our approach on two commonly-used special cases: ridges & valleys and relief edges. In each case, the optimal scale is found in accordance with the mathematical definition of the curve.
This paper addresses the problem of automatic reconstruction of a 3D relief from a line drawing o... more This paper addresses the problem of automatic reconstruction of a 3D relief from a line drawing on top of a given base object. Reconstruction is challenging due to four reasons-the sparsity of the strokes, their ambiguity, their large number, and their interrelations. Our approach is able to reconstruct a model from a complex drawing that consists of many interrelated strokes. Rather than viewing the interdependencies as a problem, we show how they can be exploited to automatically generate a good initial interpretation of the line drawing. Then, given a base and an interpretation, we propose an algorithm for reconstructing a consistent surface. The strength of our approach is demonstrated in the reconstruction of archaeological artifacts from drawings. These drawings are highly challenging, since artists created very complex and detailed descriptions of artifacts regardless of any considerations concerning their future use for shape reconstruction.
Proceedings of the 2008 ACM symposium on Virtual reality software and technology, 2008
Augmented reality is concerned with combining real-world data, such as images, with artificial da... more Augmented reality is concerned with combining real-world data, such as images, with artificial data. Texture replacement is one such task. It is the process of painting a new texture over an existing textured image patch, such that depth cues are maintained. This paper proposes a general and automatic approach for performing texture replacement, which is based on multiview stereo techniques that produce depth information at every pixel. The use of several images allows us to address the inherent limitation of previous studies, which are constrained to specific texture classes, such as textureless or near-regular textures. To be able to handle general textures, a modified dense correspondence estimation algorithm is designed and presented.
We present a novel technique for creating realistic facial animations given a small number of rea... more We present a novel technique for creating realistic facial animations given a small number of real images and a few parameters for the in-between images. This scheme can also be used for reconstructing facial movies where the parameters can be automatically extracted from the images. The in-between images are produced without ever generating a three-dimensional model of the face. Since facial motion due to expressions are not well defined mathematically our approach is based on utilizing image patterns in facial motion. These patterns were revealed by an empirical study which analyzed and compared image motion patterns in facial expressions. The major contribution of this work is showing how parameterized "ideal" motion templates can generate facial movies for different people and different expressions, where the parameters are extracted automatically from the image sequence. To test the quality of the algorithm, image sequences (one of which was taken from a TV news broadcast) were reconstructed, yielding movies hardly distinguishable from the originals.
Presence: Teleoperators and Virtual Environments, 2004
This paper discusses the problem of inserting 3D models into a single image. The main focus of th... more This paper discusses the problem of inserting 3D models into a single image. The main focus of the paper is on the accurate recovery of the camera's parameters, so that 3D models can be inserted in the “correct” position and orientation. The paper addresses two issues. The first is an automatic extraction of the principal vanishing points from an image. The second is a theoretical and an experimental analysis of the errors. To test the concept, a system that “plants” virtual 3D objects in the image was implemented. It was tested on many indoor augmented-reality scenes. Our analysis and experiments have shown that errors in the placement of the objects are unnoticeable.
A general paradigm f o r recognizing 3 0 objects is offered, and applied to some geometric primit... more A general paradigm f o r recognizing 3 0 objects is offered, and applied to some geometric primitives (spheres, cylinders, cones, and tori). The assumption is that a curve on the surface was measured with high accuracy (for instame, by a sensory robot). Differential invariants of thte curve in one method and differential properties of curves and surfaces in the other are then used to recognize the surface. The motivation is twofold: the output of some devices is not surface range data, but such curves. So, surface invariants, which may be simpier in some cases, cannot always be obtained. Also, (a considerable speedup is obtained by using curve data, as opposed to surface data which usually contains a much higher number of points.
; I general paradigm for recognizing 3D objects is offered, and applied to some geometric primiti... more ; I general paradigm for recognizing 3D objects is offered, and applied to some geometric primitives [sphe,res, cylinders, cones, and tori). The assumption is that Q curve on the surface W Q S measured with high accuracy (for instance, by a sensory robot). Differential properties of curves and surfaces are used to recognize the surface. The motivation is t,wofold: the output of some devices is not surface range data, but such curves. So, surface invariants, which may be simpler in some cases, cannot Q~W Q Y S be obtained. Also, a consaderable speedup is obtained by using curve data, QS opposed to surface data which usually contains Q much higher number of points.
Ayellet Tal Technion, Israel (a) Input image (b) Classification by shape (c) Classification by pe... more Ayellet Tal Technion, Israel (a) Input image (b) Classification by shape (c) Classification by period (d) Generation Figure 1. Analyzing archaeological artifacts. Images of archaeological artifacts are extremely challenging to analyze, since they are eroded, broken and stained (a). Our model manages to classify these artifacts not only by shape (b), but also by historical period (c). In this figure, each ellipse bounds artifacts from the same class, demonstrating the great diversity within a class. Furthermore, our model generates a drawing of the given artifact (d), which is a standard way of archaeological documentation. The top row shows an Ibex dated to the Late Iron, whereas the bottom row shows a Lion dated to the Late Bronze.
Journal on computing and cultural heritage, Mar 1, 2013
This paper addresses the problem of automatic reconstruction of a 3D relief object from a line dr... more This paper addresses the problem of automatic reconstruction of a 3D relief object from a line drawing. Our main application is reconstruction of archaeological artifacts based on line drawings. The problem is challenging due to five reasons: the small number of orthogonal views of the object, the sparsity of the strokes, their ambiguity, their large number and their interrelations. We partition the reconstruction problem into two sub-problems. First, we reconstruct the underlying smooth base of the object from the silhouette. Assuming that the variation of bases belonging to the same class of objects is relatively small, we create the base by modifying a similar base retrieved from a database. Second, we reconstruct the relief on top of the base. Our approach is able to reconstruct the relief from a complex drawing that consists of many interrelated strokes. Rather than viewing the inter-dependencies as a problem, we show how they can be exploited to automatically generate a good initial interpretation of the line drawing. Even though our algorithm is generic, its strength is demonstrated by the reconstruction of artifacts from manual drawings taken from real archaeological reports. These drawings are highly challenging, since artists created very complex and detailed descriptions of artifacts regardless of any considerations concerning their future use for shape reconstruction.
We present a novel technique for creating realistic facial animations given a small number of rea... more We present a novel technique for creating realistic facial animations given a small number of real images and a few parameters for the in-between images. This scheme can also be used for reconstructing facial movies where the parameters can be automatically extracted from the images. The in-between images are produced without ever generating a three-dimensional model of the face. Since facial motion due to expressions are not well defined mathematically our approach is based on utilizing image patterns in facial motion. These patterns were revealed by an empirical study which analyzed and compared image motion patterns in facial expressions. The major contribution of this work is showing how parameterized "ideal" motion templates can generate facial movies for different people and different expressions, where the parameters are extracted automatically from the image sequence. To test the quality of the algorithm, image sequences (one of which was taken from a TV news broadcast) were reconstructed, yielding movies hardly distinguishable from the originals.
Presence: Teleoperators & Virtual Environments, Dec 1, 2004
This paper discusses the problem of inserting three-dimensional models into a single image. The m... more This paper discusses the problem of inserting three-dimensional models into a single image. The main focus of the paper is on the accurate recovery of the camera's parameters, so that 3D models can be inserted in the "correct" position and orientation. The paper addresses two issues. The first is an automatic extraction of the principal vanishing points from an image. The second is a theoretical and an experimental analysis of the errors. To test the concept, a system which "plants" virtual 3D objects in the image was implemented. It was tested on many indoor augmented reality scenes. Our analysis and experiments have shown that errors in the placement of the objects are un-noticeable.
Curves on objects can convey the inherent features of the shape. This paper defines a new class o... more Curves on objects can convey the inherent features of the shape. This paper defines a new class of view-independent curves, denoted demarcating curves. In a nutshell, demarcating curves are the loci of the "strongest" inflections on the surface. Due to their appealing capabilities to extract and emphasize 3D textures, they are applied to artifact illustration in archaeology, where they can serve as a worthy alternative to the expensive, time-consuming, and biased manual depiction currently used.
This paper addresses the problem of automatic reconstruction of a 3D relief from a line drawing o... more This paper addresses the problem of automatic reconstruction of a 3D relief from a line drawing on top of a given base object. Reconstruction is challenging due to four reasons-the sparsity of the strokes, their ambiguity, their large number, and their interrelations. Our approach is able to reconstruct a model from a complex drawing that consists of many interrelated strokes. Rather than viewing the interdependencies as a problem, we show how they can be exploited to automatically generate a good initial interpretation of the line drawing. Then, given a base and an interpretation, we propose an algorithm for reconstructing a consistent surface. The strength of our approach is demonstrated in the reconstruction of archaeological artifacts from drawings. These drawings are highly challenging, since artists created very complex and detailed descriptions of artifacts regardless of any considerations concerning their future use for shape reconstruction.
Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)
A general paradigm f o r recognizing 3 0 objects is offered, and applied to some geometric primit... more A general paradigm f o r recognizing 3 0 objects is offered, and applied to some geometric primitives (spheres, cylinders, cones, and tori). The assumption is that a curve on the surface was measured with high accuracy (for instame, by a sensory robot). Differential invariants of thte curve in one method and differential properties of curves and surfaces in the other are then used to recognize the surface. The motivation is twofold: the output of some devices is not surface range data, but such curves. So, surface invariants, which may be simpier in some cases, cannot always be obtained. Also, (a considerable speedup is obtained by using curve data, as opposed to surface data which usually contains a much higher number of points.
This state of the art report describes the techniques of shape analysis, and of metadata search t... more This state of the art report describes the techniques of shape analysis, and of metadata search that have been already implemented in cultural heritage or we think are useful for the GRAVITATE project. These fields are relatively disjoint, and the research and development challenge of GRAVITATE is precisely to merge them. After the review of the current literature on these fields, we end the report with common remarks on possible or plausible cross connections that suggest themselves. These considerations will be refined for the Roadmap for Research deliverable.
The GRAVITATE project is developing techniques that bring together geometric and semantic data an... more The GRAVITATE project is developing techniques that bring together geometric and semantic data analysis to provide a new and more effective method of re-associating, reassembling or reunifying cultural objects that have been broken or dispersed over time. The project is driven by the needs of archaeological institutes, and the techniques are exemplified by their application to a collection of several hundred 3D-scanned fragments of large-scale terracotta statues from Salamis, Cyprus. The integration of geometrical feature extraction and matching with semantic annotation and matching into a single decision support platform will lead to more accurate reconstructions of artefacts and greater insights into history. In this paper we describe the project and its objectives, then we describe the progress made to date towards achieving those objectives: describing the datasets, requirements and analysing the state of the art. We follow this with an overview of the architecture of the integr...
2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009
Edge detection in images has been a fundamental problem in computer vision from its early days. E... more Edge detection in images has been a fundamental problem in computer vision from its early days. Edge detection on surfaces, on the other hand, has received much less attention. The most common edges on surfaces are ridges and valleys, used for processing range images in computer vision, as well as for non-photorealistic rendering in computer graphics. We propose a new type of edges on surfaces, termed relief edges. Intuitively, the surface can be considered as an unknown smooth manifold, on top of which a local height image is placed. Relief edges are the edges of this local image. We show how to compute these edges from the local differential geometric surface properties, by fitting a local edge model to the surface. We also show how the underlying manifold and the local images can be roughly approximated and exploited in the edge detection process. Last but not least, we demonstrate the application of relief edges to artifact illustration in archaeology.
Proceedings IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems
We present a technique for reconstructing facial movies, given a small number of real images and ... more We present a technique for reconstructing facial movies, given a small number of real images and a few parameters for the in-between images. The parameters can be automatically extracted by a tracking system. This scheme can also be used for creating realistic facial animations and for compression of facial movies. The in-between images are produced without ever generating a 3D
Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)
; I general paradigm for recognizing 3D objects is offered, and applied to some geometric primiti... more ; I general paradigm for recognizing 3D objects is offered, and applied to some geometric primitives [sphe,res, cylinders, cones, and tori). The assumption is that Q curve on the surface W Q S measured with high accuracy (for instance, by a sensory robot). Differential properties of curves and surfaces are used to recognize the surface. The motivation is t,wofold: the output of some devices is not surface range data, but such curves. So, surface invariants, which may be simpler in some cases, cannot Q~W Q Y S be obtained. Also, a consaderable speedup is obtained by using curve data, QS opposed to surface data which usually contains Q much higher number of points.
Collision detection is a fundamental problem in computer graphics. In this paper, temporal cohere... more Collision detection is a fundamental problem in computer graphics. In this paper, temporal coherence is studied and an algorithm exploiting it for bounding volume hierarchies, is presented. We show that maintaining some of the intersection tests computed in the previous frame, along with certain information, is able to speedup the intersection tests considerably. The algorithm is able to accelerate the collision detection for small motions and works as fast as the regular algorithm for large motions, where temporal coherence does not exist. The algorithm framework can be implemented for any type of bounding volume hierarchy. To demonstrate this, it was implemented for the OBB and the AABB data structures and tested on several benchmark scenarios.
2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013
This paper extends to surfaces the multi-scale approach of edge detection on images. The common p... more This paper extends to surfaces the multi-scale approach of edge detection on images. The common practice for detecting curves on surfaces requires the user to first select the scale of the features, apply an appropriate smoothing, and detect the edges on the smoothed surface. This approach suffers from two drawbacks. First, it relies on a hidden assumption that all the features on the surface are of the same scale. Second, manual user intervention is required. In this paper, we propose a general framework for automatically detecting the optimal scale for each point on the surface. We smooth the surface at each point according to this optimal scale and run the curve detection algorithm on the resulting surface. Our multi-scale algorithm solves the two disadvantages of the single-scale approach mentioned above. We demonstrate how to realize our approach on two commonly-used special cases: ridges & valleys and relief edges. In each case, the optimal scale is found in accordance with the mathematical definition of the curve.
This paper addresses the problem of automatic reconstruction of a 3D relief from a line drawing o... more This paper addresses the problem of automatic reconstruction of a 3D relief from a line drawing on top of a given base object. Reconstruction is challenging due to four reasons-the sparsity of the strokes, their ambiguity, their large number, and their interrelations. Our approach is able to reconstruct a model from a complex drawing that consists of many interrelated strokes. Rather than viewing the interdependencies as a problem, we show how they can be exploited to automatically generate a good initial interpretation of the line drawing. Then, given a base and an interpretation, we propose an algorithm for reconstructing a consistent surface. The strength of our approach is demonstrated in the reconstruction of archaeological artifacts from drawings. These drawings are highly challenging, since artists created very complex and detailed descriptions of artifacts regardless of any considerations concerning their future use for shape reconstruction.
Proceedings of the 2008 ACM symposium on Virtual reality software and technology, 2008
Augmented reality is concerned with combining real-world data, such as images, with artificial da... more Augmented reality is concerned with combining real-world data, such as images, with artificial data. Texture replacement is one such task. It is the process of painting a new texture over an existing textured image patch, such that depth cues are maintained. This paper proposes a general and automatic approach for performing texture replacement, which is based on multiview stereo techniques that produce depth information at every pixel. The use of several images allows us to address the inherent limitation of previous studies, which are constrained to specific texture classes, such as textureless or near-regular textures. To be able to handle general textures, a modified dense correspondence estimation algorithm is designed and presented.
We present a novel technique for creating realistic facial animations given a small number of rea... more We present a novel technique for creating realistic facial animations given a small number of real images and a few parameters for the in-between images. This scheme can also be used for reconstructing facial movies where the parameters can be automatically extracted from the images. The in-between images are produced without ever generating a three-dimensional model of the face. Since facial motion due to expressions are not well defined mathematically our approach is based on utilizing image patterns in facial motion. These patterns were revealed by an empirical study which analyzed and compared image motion patterns in facial expressions. The major contribution of this work is showing how parameterized "ideal" motion templates can generate facial movies for different people and different expressions, where the parameters are extracted automatically from the image sequence. To test the quality of the algorithm, image sequences (one of which was taken from a TV news broadcast) were reconstructed, yielding movies hardly distinguishable from the originals.
Presence: Teleoperators and Virtual Environments, 2004
This paper discusses the problem of inserting 3D models into a single image. The main focus of th... more This paper discusses the problem of inserting 3D models into a single image. The main focus of the paper is on the accurate recovery of the camera's parameters, so that 3D models can be inserted in the “correct” position and orientation. The paper addresses two issues. The first is an automatic extraction of the principal vanishing points from an image. The second is a theoretical and an experimental analysis of the errors. To test the concept, a system that “plants” virtual 3D objects in the image was implemented. It was tested on many indoor augmented-reality scenes. Our analysis and experiments have shown that errors in the placement of the objects are unnoticeable.
Uploads
Papers by Ilan Shimshoni