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 this paper a system is presented that automatically registers and stitches textures acquired from multiple photographic images onto the surface of a given corresponding 3D model. Within this process the camera position, direction, and field of view must be determined for each of the images. For this registration, which aligns a 2D image to a 3D model, we present an efficient hardware-accelerated silhouette-based algorithm working on different image resolutions that accurately registers each image without any user interaction. Besides the silhouettes, the given texture information also can be used to improve accuracy by comparing one stitched texture to already registered images resulting in a global multiview optimization. After the 3D?2D registration for each part of the 3D model's surface the view is determined which provides the best available texture. Textures are blended at the borders of regions assigned to different views.

/pdf/a-silhouette-based-algorithm-for-texture-registration-and-4newvgpm7o.pdf

A Silhouette-Based Algorithm for Texture Registration and Stitching

Environment maps are widely used for approximating reflections in hardware-accelerated rendering applications. Unfortunately, the parameterizations for environment maps used in today’s graphics hardware severely undersample certain directions, and can thus not be used from multiple viewing directions. Other parameterizations exist, but require operations that would be too expensive for hardware implementations. In this paper we introduce an inexpensive new parameterization for environment maps that allows us to reuse the environment map for any given viewing direction. We describe how, under certain restrictions, these maps can be used today in standard OpenGL implementations. Furthermore, we explore how OpenGL could be extended to support this kind of environment map more directly. CR Categories: 1.3.1 [Computer Graphics]: Hardware Architecture-Graphics processors; 1.3.3 [Computer Graphics]: Picture/Image Generation-Bitmap and framebuffer operations; 1.3.6 [Computer Graphics]: Methodology and Techniques--Standards 1.3.7 [Computer Graphics]: ThreeDimensional Graphics and Realism-Color, Shading, Shadowing and Texture 1.4.1 [Image Processing and Computer Vision]: Digitization and Image Capture ~-Sampling

View-independent environment maps

With fast3D graphicsbecomingmoreandmoreavailableevenon low endplatforms,thefocusin developingnew graphicshardware is beginning to shift towardshigher quality renderingand additional functionality insteadof simply higher performanceimplementationsof the traditionalgraphicspipeline. On this searchfor improved quality it is importantto identify a powerful set of orthogonalfeaturesto be implementedin hardware,which canthen beflexibly combinedto form new algorithms. Pixel texturesareanOpenGLextensionby SiliconGraphicsthat fits into this category. In this paper , we demonstratethebenefitsof thisextensionby presentingseveraldifferentalgorithmsexploiting its functionalityto achievehighquality, highperformancesolutions for a variety of differentapplicationsfrom scientificvisualization andrealisticimagesynthesis.Weconcludethatpixel texturesarea valuable,powerful featurethatshouldbecomea standardin future graphicssystems. CR Categories: I.3.3 [Computer Graphics]: Picture/Image Generation—Bitmapand framebuffer operationsI.3.3 [Computer Graphics]: Picture/ImageGeneration—Displayalgorithms I.3.6 [ComputerGraphics]: Methodologyand Techniques—Standards I.3.7 [Computer Graphics]: Three-DimensionalGraphics and Realism—Color , Shading,Shadowing andTexture

Applications of pixel textures in visualization and realistic image synthesis

We propose texture maps that contain at each texel all the parameters of a Lafortune representation BRDF as a compact, but quite general surface appearance representation. We describe a method for rendering such surfaces rapidly on current graphics hardware and demonstrate the method with real, measured surfaces and hand-painted surfaces.We also propose a method of rendering such spatial bi-directional reflectance distribution functions using prefiltered environment maps. Only one set of maps is required for rendering the different BRDFs stored at each texel over the surface.

/pdf/efficient-rendering-of-spatial-bi-directional-reflectance-2knxj10faq.pdf

Efficient rendering of spatial bi-directional reflectance distribution functions

We present a self-identifying marker pattern for camera calibration, together with the associated detection algorithm. The pattern is designed to support high-precision, fully-automatic localization of calibration points, as well as identification of individual markers in the presence of significant occlusions, uneven illumination, and observations under extremely acute angles. The detection algorithm is efficient and free of parameters. After calibration we obtain reprojection errors significantly lower than with state-of-the art self-identifying reference patterns.

Wolfgang Heidrich

Papers

A Silhouette-Based Algorithm for Texture Registration and Stitching

View-independent environment maps

Applications of pixel textures in visualization and realistic image synthesis

Efficient rendering of spatial bi-directional reflectance distribution functions

CALTag: High Precision Fiducial Markers for Camera Calibration