Shape from defocus via diffusion

Defocus can be modeled as a diffusion process and represented mathematically using the heat equation, where image blur corresponds to the diffusion of heat. This analogy can be extended to non-planar scenes by allowing a space-varying diffusion coefficient. The inverse problem of reconstructing 3-D structure from blurred images corresponds to an "inverse diffusion" that is notoriously ill-posed. We show how to bypass this problem by using the notion of relative blur. Given two images, within each neighborhood, the amount of diffusion necessary to transform the sharper image into the blurrier one depends on the depth of the scene. This can be used to devise a global algorithm to estimate the depth profile of the scene without recovering the deblurred image, using only forward diffusion.     

Dynamic Shape and Appearance Modeling via Moving and Deforming Layers

We propose a model of the shape, motion and appearance of a scene, seen through a sequence of images, that captures occlusions, scene deformations, unconstrained viewpoint variations and changes in its radiance. This model is based on a collection of overlapping layers that can move and deform, each supporting an intensity function that can change over time. We discuss the generality and limitations of this model in relation to existing ones such as traditional optical flow or motion segmentation, layers, deformable templates and deformotion. We then illustrate how this model can be used for inference of shape, motion, deformation and appearance of the scene from a collection of images. The layering structure allows for automatic inpainting of partially occluded regions. We illustrate the model on synthetic and real sequences where existing schemes fail, and show how suitable choices of constants in the model yield existing schemes, from optical flow to motion segmentation and inpainting.     

Classification and recognition of dynamical models: the role of phase, independent components, kernels and optimal transport

We address the problem of performing decision tasks, and in particular classification and recognition, in the space of dynamical models in order to compare time series of data. Motivated by the application of recognition of human motion in image sequences, we consider a class of models that include linear dynamics, both stable and marginally stable (periodic), both minimum and non-minimum phase, driven by non-Gaussian processes. This requires extending existing learning and system identification algorithms to handle periodic modes and nonminimum phase behavior, while taking into account higher-order statistics of the data. Once a model is identified, we define a kernel-based cord distance between models that includes their dynamics, their initial conditions as well as input distribution. This is made possible by a novel kernel defined between two arbitrary (non-Gaussian) distributions, which is computed by efficiently solving an optimal transport problem. We validate our choice of models, inference algorithm, and distance on the tasks of human motion synthesis (sample paths of the learned models), and recognition (nearest-neighbor classification in the computed distance). However, our work can be applied more broadly where one needs to compare historical data while taking into account periodic trends, non-minimum phase behavior, and non-Gaussian input distributions.     

A variational approach to problems in calibration of multiple cameras

This paper addresses the problem of calibrating camera parameters using variational methods. One problem addressed is the severe lens distortion in low-cost cameras. For many computer vision algorithms aiming at reconstructing reliable representations of 3D scenes, the camera distortion effects will lead to inaccurate 3D reconstructions and geometrical measurements if not accounted for. A second problem is the color calibration problem caused by variations in camera responses that result in different color measurements and affects the algorithms that depend on these measurements. We also address the extrinsic camera calibration that estimates relative poses and orientations of multiple cameras in the system and the intrinsic camera calibration that estimates focal lengths and the skew parameters of the cameras. To address these calibration problems, we present multiview stereo techniques based on variational methods that utilize partial and ordinary differential equations. Our approach can also be considered as a coordinated refinement of camera calibration parameters. To reduce computational complexity of such algorithms, we utilize prior knowledge on the calibration object, making a piecewise smooth surface assumption, and evolve the pose, orientation, and scale parameters of such a 3D model object without requiring a 2D feature extraction from camera views. We derive the evolution equations for the distortion coefficients, the color calibration parameters, the extrinsic and intrinsic parameters of the cameras, and present experimental results.     

Integral invariants for shape matching

For shapes represented as closed planar contours, we introduce a class of functionals which are invariant with respect to the Euclidean group and which are obtained by performing integral operations. While such integral invariants enjoy some of the desirable properties of their differential counterparts, such as locality of computation (which allows matching under occlusions) and uniqueness of representation (asymptotically), they do not exhibit the noise sensitivity associated with differential quantities and, therefore, do not require presmoothing of the input shape. Our formulation allows the analysis of shapes at multiple scales. Based on integral invariants, we define a notion of distance between shapes. The proposed distance measure can be computed efficiently and allows warping the shape boundaries onto each other; its computation results in optimal point correspondence as an intermediate step. Numerical results on shape matching demonstrate that this framework can match shapes despite the deformation of subparts, missing parts and noise. As a quantitative analysis, we report matching scores for shape retrieval from a database.     

Optimal Structure from Motion: Local Ambiguities and Global Estimates

Structure From Motion (SFM) refers to the problem of estimating spatial properties of a three-dimensional scene from the motion of its projection onto a two-dimensional surface, such as the retina. We present an analysis of SFM which results in algorithms that are provably convergent and provably optimal with respect to a chosen norm.In particular, we cast SFM as the minimization of a high-dimensional quadratic cost function, and show how it is possible to reduce it to the minimization of a two-dimensional function whose stationary points are in one-to-one correspondence with those of the original cost function. As a consequence, we can plot the reduced cost function and characterize the configurations of structure and motion that result in local minima. As an example, we discuss two local minima that are associated with well-known visual illusions. Knowledge of the topology of the residual in the presence of such local minima allows us to formulate minimization algorithms that, in addition to provably converge to stationary points of the original cost function, can switch between different local extrema in order to converge to the global minimum, under suitable conditions. We also offer an experimental study of the distribution of the estimation error in the presence of noise in the measurements, and characterize the sensitivity of the algorithm using the structure of Fisher's Information matrix.     

Recursive 3-D Visual Motion Estimation Using Subspace Constraints

A structure from motion algorithm is described which recovers structure and camera position, modulo a projective ambiguity. Camera calibration is not required, and camera parameters such as focal length can be altered freely during motion. The structure is updated sequentially over an image sequence, in contrast to schemes which employ a batch process. A specialisation of the algorithm to recover structure and camera position modulo an affine transformation is described, together with a method to periodically update the affine coordinate frame to prevent drift over time. We describe the constraint used to obtain this specialisation.Structure is recovered from image corners detected and matched automatically and reliably in real image sequences. Results are shown for reference objects and indoor environments, and accuracy of recovered structure is fully evaluated and compared for a number of reconstruction schemes. A specific application of the work is demonstrated—affine structure is used to compute free space maps enabling navigation through unstructured environments and avoidance of obstacles. The path planning involves only affine constructions.     

Structure from motion causally integrated over time

We describe an algorithm for reconstructing three-dimensional structure and motion causally, in real time from monocular sequences of images. We prove that the algorithm is minimal and stable, in the sense that the estimation error remains bounded with probability one throughout a sequence of arbitrary length. We discuss a scheme for handling occlusions (point features appearing and disappearing) and drift in the scale factor. These issues are crucial for the algorithm to operate in real time on real scenes. We describe in detail the implementation of the algorithm, which runs on a personal computer and has been made available to the community. We report the performance of our implementation on a few representative long sequences of real and synthetic images. The algorithm, which has been tested extensively over the course of the past few years, exhibits honest performance when the scene contains at least 20-40 points with high contrast, when the relative motion is "slow" compared to the sampling frequency of the frame grabber (30 Hz), and the lens aperture is "large enough" (typically more than 30° of visual field)     

Information-Seeking Control Under Visibility-Based Uncertainty

We address the problem of exploring an unknown environment using a range sensor. In the presence of opaque objects of arbitrary shape and topology, exploration is driven by minimization of residual uncertainty, that is primarily due to lack of visibility. The resulting optimal control is approximated with a computationally efficient heuristic, that is proven to complete exploration of a compact environment in a finite number of steps.