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

Image-Based Rendering

Recent years have seen an explosion of the number of camera modules integratedinto individual consumer mobile devices, including configurations that contain multi-ple different types of image sensors. One popular configuration is to combine an RGBcamera for color imaging with a monochrome camera that has improved performancein low-light settings, as well as some sensitivity in the infrared. In this work we in-troduce a method to combine simultaneously captured images from such a two-camerastereo system to generate a high-quality, noise reduced color image. To do so, pixel-to-pixel alignment has to be constructed between the two captured monochrome and colorimages, which however, is prone to artifacts due to parallax. The joint image recon-struction is made robust by introducing a novel artifact-robust optimization formulation.We provide extensive experimental results based on the two-camera configuration of a commercially available cell phone.

https://hal.inria.fr/hal-02370233/document

Robust Joint Image Reconstruction from Color and Monochrome Cameras.

We present a 360° light field display to visualize 3D objects above the table-top screen, and provide a graspable and measurable virtual or augmented reality environment. The display is constructed by a spinning flat-plate deflected diffuser screen, a high-speed light field projector, and the user tracking and interaction components. A rear projection light propagation is specially designed to reconstruct the light field. By calibrating this levitated light field to the physical dimension, and capturing user gestures, we enable multiple users mid-air interactions based on their virtual measurement perception.

Towards VR and AR enhancement: light field display with mid-air interaction

Many visual difference predictors (VDPs) have used basic psychophysical data (such as ModelFest) to calibrate the
algorithm parameters and to validate their performances. However, the basic psychophysical data often do not contain
sufficient number of stimuli and its variations to test more complex components of a VDP. In this paper we calibrate the
Visual Difference Predictor for High Dynamic Range images (HDR-VDP) using radiologists' experimental data for
JPEG2000 compressed CT images which contain complex structures. Then we validate the HDR-VDP in predicting the
presence of perceptible compression artifacts. 240 CT-scan images were encoded and decoded using JPEG2000
compression at four compression ratios (CRs). Five radiologists participated to independently determine if each image
pair (original and compressed images) was indistinguishable or distinguishable. A threshold CR for each image, at which
50% of radiologists would detect compression artifacts, was estimated by fitting a psychometric function. The CT
images compressed at the threshold CRs were used to calibrate the HDR-VDP parameters and to validate its prediction
accuracy. Our results showed that the HDR-VDP calibrated for the CT image data gave much better predictions than the
HDR-VDP calibrated to the basic psychophysical data (ModelFest + contrast masking data for sine gratings).

/pdf/calibration-of-the-visual-difference-predictor-for-25a918gxt9.pdf

Calibration of the visual difference predictor for estimating visibility of JPEG2000 compression artifacts in CT images

This work was supported by King Abdullah University of Science and Technology as part of VCC center baseline funding.

Wolfgang Heidrich

Papers

Image-Based Rendering

Robust Joint Image Reconstruction from Color and Monochrome Cameras.

Towards VR and AR enhancement: light field display with mid-air interaction

Calibration of the visual difference predictor for estimating visibility of JPEG2000 compression artifacts in CT images

Stochastic Convolutional Sparse Coding