The present paper proposes a versatile procedure for the geometrical calibration of coded aperture gamma cameras and RGB-D depth sensors, using only one radioactive point source and a simple experimental set-up. Calibration data is then used for accurately aligning radiation images retrieved by means of the γ-camera with the respective depth images computed with the RGB-D sensor. The system resulting from such a combination is thus able to retrieve, automatically, the distance of radioactive hotspots by means of pixel-wise mapping between gamma and depth images. This procedure is of great interest for a wide number of applications, ranging from precise automatic estimation of the shape and distance of radioactive objects to Augmented Reality systems. Incidentally, the corresponding results validated the choice of a perspective design model for a coded aperture γ-camera.

We present an algorithm for estimating the pose of a rigid object in real-time under challenging conditions. Our method effectively handles poorly textured objects in cluttered, changing environments, even when their appearance is corrupted by large occlusions, and it relies on grayscale images to handle metallic environments on which depth cameras would fail. As a result, our method is suitable for practical Augmented Reality applications including industrial environments. At the core of our approach is a novel representation for the 3D pose of object parts: We predict the 3D pose of each part in the form of the 2D projections of a few control points. The advantages of this representation is three-fold: We can predict the 3D pose of the object even when only one part is visible; when several parts are visible, we can easily combine them to compute a better pose of the object; the 3D pose we obtain is usually very accurate, even when only few parts are visible. We show how to use this representation in a robust 3D tracking framework. In addition to extensive comparisons with the state-of-the-art, we demonstrate our method on a practical Augmented Reality application for maintenance assistance in the ATLAS particle detector at CERN.

We propose new algorithms to overcome two of the most constraining limitations of surface reconstruction methods in use. In particular, we focus on the large amount of data characterizing standard acquisitions by scanner and the noise intrinsically introduced by measurements. The first algorithm represents an adaptive multi-level interpolating approach, based on an implicit surface representation via radial basis functions. The second algorithm is based on a least-squares approximation to filter noisy data. The third approach combines the two algorithms to merge the correspondent improvements. An extensive numerical validation is performed to check the performances of the proposed techniques.

We present a method that estimates in real-time and under challenging conditions the 3D pose of a known object. Our method relies only on grayscale images since depth cameras fail on metallic objects, it can handle poorly textured objects, and cluttered, changing environments, the pose it predicts degrades gracefully in presence of large occlusions. As a result, by contrast with the state-of-the-art, our method is suitable for practical Augmented Reality applications even in industrial environments. To be robust to occlusions, we first learn to detect some parts of the target object. Our key idea is to then predict the 3D pose of each part in the form of the 2D projections of a few control points. The advantages of this representation is three-fold: We can predict the 3D pose of the object even when only one part is visible, when several parts are visible, we can combine them easily to compute a better pose of the object, the 3D pose we obtain is usually very accurate, even when only few parts are visible.

Deformable surface tracking from monocular images is well-known to be under-constrained. Occlusions often make the task even more challenging, and can result in failure if the surface is not sufficiently textured. In this work, we explicitly address the problem of 3D reconstruction of poorly textured, occluded surfaces, proposing a framework based on a template-matching approach that scales dense robust features by a relevancy score. Our approach is extensively compared to current methods employing both local feature matching and dense template alignment. We test on standard datasets as well as on a new dataset (that will be made publicly available) of a sparsely textured, occluded surface. Our framework achieves state-of-the-art results for both well and poorly textured, occluded surfaces.

Deformable surface tracking from monocular images is a well-known under-constrained problem. Occlusions often make the task even more challenging, and can lead current methods to fail if the surface is not sufficiently textured. In this work, we explicitly address the problem of 3D reconstruction of poorly textured, occluded surfaces, proposing a framework based on a template-matching approach that scales dense robust features by a relevancy score. Our approach is extensively compared to current methods employing both local feature matching and dense template alignment. We test on standard datasets as well as on a new dataset (that will be made publicly available) of a sparsely textured, occluded surface. Our framework achieves state-of-the-art results for both well and poorly textured, occluded surfaces.

This survey focuses on a class of methods for image alignment based on a global, iterative optimization. We update the important survey from Baker and Matthews [2], synthetically describing the existing methods (included the recent Efficient Second Order Method, not covered by [2]), comparing their theoretical aspects, computational costs and implementation issues, and describing an example of application to 3D tracking, involving a complex, non-linear warp.

This survey focuses on a class of methods for image alignment based on a global, iterative optimization. We synthetically describe the existing methods (included the recent Efficient Second Order Method), compare their theoretical aspects, computational costs and implementation issues, and finally present an example of application to 3D tracking, involving a complex, non-linear warp.

Our demo demonstrates the method we published at CVPR this year for tracking specular and poorly textured objects, and lets the visitors experiment with it and with their own patterns. Our approach only requires a standard monocular camera (no need for a depth sensor), and can be easily integrated within existing systems to improve their robustness and accuracy.

We introduce a method that can register challenging images from specular and poorly textured 3D environments, on which previous approaches fail.We assume that a small set of reference images of the environment and a partial 3D model are available.Like previous approaches, we register the input images by aligning them with one of the reference images using the 3D information.However, these approaches typically rely on the pixel intensities for the alignment, which is prone to fail in presence of specularities or in absence of texture.Our main contribution is an efficient novel local descriptor that we use to describe each image location.We show that we can rely on this descriptor in place of the intensities to significantly improve the alignment robustness at a minor increase of the computational cost, and we analyze the reasons behind the success of our descriptor.