We show a learning-based method for low-level vision problems. We set-up a Markov network of patches of the image and the underlying scene. A factorization approximation allows us to easily learn the parameters of the Markov network from synthetic examples of image/scene pairs, and to e ciently propagate image information. Monte Carlo simulations justify this approximation. We apply this to the \super-resolution " problem (estimating high frequency details from a low-resolution image), showing good results. For the motion estimation problem, we show resolution of the aperture problem and lling-in arising from application of the same probabilistic machinery.

This paper presents a comparative study and survey of model-based object-recognition algorithms for robot vision. The goal of these algorithms is to recognize the identity, position, and orientation of randomly oriented industrial parts. In one form this is commonly referred to as the “bin-picking ” problem, in which the parts to be recognized are presented in a jumbled bin. The paper is organized according to 2-D, 2&D, and 3-D object representations, which are used as the basis for the recognition algorithms. Three

and should not be interpreted as necessarily representing o cial policies or endorsements,

A new method named STM is described for determining distance of objects and rapid autofocusing of camera systems. STM uses image defocus information and is based on a new Spatial-Domain Convolution/Deconvolution Transform. The method requires only two images taken with dierent camera parameters such as lens position, focal length, and aperture diameter. Both images can be arbitrarily blurred and neither of them needs to be a focused image. Therefore STM is very fast in comparison with Depth-from-Focus methods which search for the lens position or focal length of best focus. The method involves simple local operations and can be easily implemented in parallel to obtain the depthmap of a scene. STM has been implemented on an actual camera system named SPARCS. Experiments on the performance of STM and their results on realworld planar objects are presented. The results indicate that the accuracy of STM compares well with Depth-from-Focus methods and is useful in practical ap...

A new method is described for recovering the distance of objects in a scene from images formed by lenses. The recovery is based on measuring the change in the scene's image due to a known change in the three intrinsic camera parameters: (i) distance between the lens and the image detector, (ii) focal length of the lens, and (iii) diameter of the lens aperture. The method is parallel involving simple local computations. In comparison with stereo vision and structure-frommotion methods, the correspondence problem does not arise. This method for depth-map recovery may also be used for (i) obtaining focused images (i.e. images having large depth of field) from two images having finite depth of field, and (ii) rapid autofocusing of computer controlled video cameras. 1. Introduction Here we describe a new passive ranging method which in principle is fast and involves relatively weak assumptions that are generally valid. The method is basically a generalized version of the `depth-from-focu...

This paper studies the problem of obtaining depth information from focusing and defocusing, which have long been noticed as important sources of depth information for human and machine vision. In depth from focusing, we try to eliminate the local maxima problem which is the main source of inaccuracy in focusing; in depth from defocusing, a new computational model is proposed to achieve higher accuracy. The major contributions of this paper are: (1) In depth from focusing, instead of the popular Fibonacci search which is often trapped in local maxima, we propose the combination of Fibonacci search and curve fitting, which leads to an unprecedentedly accurate result; (2) New model of the blurring effect which takes the geometric blurring as well as the imaging blurring into consideration, and the calibration of the blurring model; (3) In spectrogram-based depth from defocusing, an iterative estimation method is proposed to decrease or eliminate the window effect. This paper reports focus...

We use the paraxial geometric optics model of image formation to derive a set of camera focusing techniques. These techniques do not require calibration of cameras but involve a search of the camera parameter space. The techniques are proved to be theoretically sound. They include energy maximization of unltered, low-pass ltered, highpass ltered, and band-pass ltered images. It is shown that in the presence of high spatial frequencies, noise, and aliasing, focusing techniques based on band-pass lters perform well. The focusing techniques are implemented on a a prototype camera system named SPARCS. The architecture of SPARCS is described briey. The performance of the dierent techniques are compared experimentally. All techniques are found to perform well. One of them which has better overall characteristics is recommended for practical applications. 1 Introduction Focusing cameras is an important problem in computer vision and microscopy. In this paper we consider only those pas...

. We address the problem of computing a general-purpose early visual representation that satisfies two criteria. 1) Explicitness: To be more useful than the original pixel array, the representation must take a significant step toward making important image structure explicit. 2) Completeness: To support a diverse set of high-level tasks, the representation must not discard information of potential perceptual relevance. The most prevalent representation in image processing and computer vision that satisfies the completeness criterion is the wavelet code. In this paper, we propose a very different code which represents the location of each edge and the magnitude and blur scale of the underlying intensity change. By making edge structure explicit, we argue that this representation better satisfies the first criterion than do wavelet codes. To address the second criterion, we study the question of how much visual information is lost in the representation. We report a novel method for inver...

The image of a scene formed by an optical system such as a lens contains both photometric and geometric information about the scene. `Inverse Optics' is the problem of recovering this information from a set of images sensed by the camera. Previous solutions to this problem-- the depth-from-focusing methods-- required a large number (in principle, infinitely many) of images to be recorded and processed. Hence the methods were slow and computationally intensive. Recent work in this area suggests solutions that require only a few images and therefore are fast and computationally efficient. Here we present a coherent view of recent developments. Theoretical principles, practical issues, and unsolved problems are discussed. Preliminary experimental results are presented.

This paper describes attempts to model the modules of early vision in terms of minimizing energy functions, in particular energy functions allowing discontinuities in the solution. It examines the success of using Hopfield-style analog networks for solving such problems. Finally it discusses the limitations of the energy function approach.