This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.

/pdf/distinctive-image-features-from-scale-invariant-keypoints-3waurjqzke.pdf

Distinctive Image Features from Scale-Invariant Keypoints

Humans perceive the three-dimensional structure of the world with apparent ease. However, despite all of the recent advances in computer vision research, the dream of having a computer interpret an image at the same level as a two-year old remains elusive. Why is computer vision such a challenging problem and what is the current state of the art? Computer Vision: Algorithms and Applications explores the variety of techniques commonly used to analyze and interpret images. It also describes challenging real-world applications where vision is being successfully used, both for specialized applications such as medical imaging, and for fun, consumer-level tasks such as image editing and stitching, which students can apply to their own personal photos and videos. More than just a source of recipes, this exceptionally authoritative and comprehensive textbook/reference also takes a scientific approach to basic vision problems, formulating physical models of the imaging process before inverting them to produce descriptions of a scene. These problems are also analyzed using statistical models and solved using rigorous engineering techniques Topics and features: structured to support active curricula and project-oriented courses, with tips in the Introduction for using the book in a variety of customized courses; presents exercises at the end of each chapter with a heavy emphasis on testing algorithms and containing numerous suggestions for small mid-term projects; provides additional material and more detailed mathematical topics in the Appendices, which cover linear algebra, numerical techniques, and Bayesian estimation theory; suggests additional reading at the end of each chapter, including the latest research in each sub-field, in addition to a full Bibliography at the end of the book; supplies supplementary course material for students at the associated website, http://szeliski.org/Book/. Suitable for an upper-level undergraduate or graduate-level course in computer science or engineering, this textbook focuses on basic techniques that work under real-world conditions and encourages students to push their creative boundaries. Its design and exposition also make it eminently suitable as a unique reference to the fundamental techniques and current research literature in computer vision.

/pdf/computer-vision-algorithms-and-applications-25dn6wu83j.pdf

Computer Vision: Algorithms and Applications

While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics today, such as PSNR and SSIM, are simple, shallow functions, and fail to account for many nuances of human perception. Recently, the deep learning community has found that features of the VGG network trained on ImageNet classification has been remarkably useful as a training loss for image synthesis. But how perceptual are these so-called "perceptual losses"? What elements are critical for their success? To answer these questions, we introduce a new dataset of human perceptual similarity judgments. We systematically evaluate deep features across different architectures and tasks and compare them with classic metrics. We find that deep features outperform all previous metrics by large margins on our dataset. More surprisingly, this result is not restricted to ImageNet-trained VGG features, but holds across different deep architectures and levels of supervision (supervised, self-supervised, or even unsupervised). Our results suggest that perceptual similarity is an emergent property shared across deep visual representations.

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

On robust estimation of the location parameter

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

In the past few years Tcl has found widespread interest as a extensible scripting language. Numerous Tcl interfaces for a variety of C libraries have been created. While most of these language bindings have been created by hand, others have made use of dedicated code generators designed for the specific library.

In this paper we present a tool for the automatic generation of Tcl language bindings for arbitrary C libraries. Moreover, the mapping of C++ class hierarchies to [incr Tcl] classes will be described.

Automatic generation of Tcl bindings for C and C++ libraries

We present an image formation model for deterministic phase retrieval in propagation-based wavefront sensing, unifying analysis for classical wavefront sensors such as Shack-Hartmann (slopes tracking) and curvature sensors (based on Transport-of-Intensity Equation). We show how this model generalizes commonly seen formulas, including Transport-of-Intensity Equation, from small distances and beyond. Using this model, we analyze theoretically achievable lateral wavefront resolution in propagation-based deterministic wavefront sensing. Finally, via a prototype masked wavefront sensor, we show simultaneous bright field and phase imaging numerically recovered in real-time from a single-shot measurement.

Modeling classical wavefront sensors.

In this document we explore the theory and potential experimental setups for measuring the near field of a complex luminary This work extends on near field photometry by taking filtering issues into account The physical measurement setups described here have not been tested at the time of writing this document, we simply describe several possibilities here Once actual tests have been performed, the results will be published elsewhere

http://domino.mpi-inf.mpg.de/intranet/ag4/ag4publ.nsf/2a3e8aac13d8697cc125675300686237/1b9a2767f0cba726c1256cfc00408a8c/$file/tr-2001-08.pdf

Image-Based Measurement of Light Sources With Correct Filtering

This chapter introduces techniques for the capture and efficient display of dynamic three-dimensional non-stationary gas flows. We describe a flexible Schlieren-tomographic system consisting of multiple consumer camcorders. A special choice of background pattern for Background Oriented Schlieren (BOS) imaging provides for flexibility in the experimental setup. Optical flow techniques are used to measure image space deflections due to heated air flows from arbitrary camera positions. A specially tailored sparse-view algebraic reconstruction algorithm is employed to tomographically recover a refractive index gradient field. After robust integration of these gradient fields, time-varying, fully three-dimensional refractive index fields are obtained. These can be rendered efficiently using a ray-casting style algorithm that is suitable for graphics hardware acceleration. Additional optical properties can be rendered within the same computational framework.

Tomographic Reconstruction and Efficient Rendering of Refractive Gas Flows

We introduce Mask-ToF, a method to reduce flying pixels (FP) in time-of-flight (ToF) depth captures. FPs are pervasive artifacts which occur around depth edges, where light paths from both an object and its background are integrated over the aperture. This light mixes at a sensor pixel to produce erroneous depth estimates, which can adversely affect downstream 3D vision tasks. Mask-ToF starts at the source of these FPs, learning a microlens-level occlusion mask which effectively creates a custom-shaped sub-aperture for each sensor pixel. This modulates the selection of foreground and background light mixtures on a per-pixel basis and thereby encodes scene geometric information directly into the ToF measurements. We develop a differentiable ToF simulator to jointly train a convolutional neural network to decode this information and produce high-fidelity, low-FP depth reconstructions. We test the effectiveness of Mask-ToF on a simulated light field dataset and validate the method with an experimental prototype. To this end, we manufacture the learned amplitude mask and design an optical relay system to virtually place it on a high-resolution ToF sensor. We find that Mask-ToF generalizes well to real data without retraining, cutting FP counts in half.

/pdf/mask-tof-learning-microlens-masks-for-flying-pixel-49svaczkpp.pdf

Wolfgang Heidrich

Papers

Automatic generation of Tcl bindings for C and C++ libraries

Modeling classical wavefront sensors.

Image-Based Measurement of Light Sources With Correct Filtering

Tomographic Reconstruction and Efficient Rendering of Refractive Gas Flows

Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging