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

Correlation image sensors have recently become popular low-cost devices for time-of-flight, or range cameras. They usually operate under the assumption of a single light path contributing to each pixel. We show that a more thorough analysis of the sensor data from correlation sensors can be used can be used to analyze the light transport in much more complex environments, including applications for imaging through scattering and turbid media. The key of our method is a new convolutional sparse coding approach for recovering transient (light-in-flight) images from correlation image sensors. This approach is enabled by an analysis of sparsity in complex transient images, and the derivation of a new physically-motivated model for transient images with drastically improved sparsity.

Imaging in scattering media using correlation image sensors and sparse convolutional coding

An electronic camera comprises two or more image sensor arrays. At least one of the image sensor arrays has a high dynamic range. The camera also comprises a shutter for selectively allowing light to reach the two or more image sensor arrays, readout circuitry for selectively reading out pixel data from the image sensor arrays, and, a controller configured to control the shutter and the readout circuitry. The controller comprises a processor and a memory having computer-readable code embodied therein which, when executed by the processor, causes the controller to open the shutter for an image capture period to allow the two or more image sensor arrays to capture pixel data, and, read out pixel data from the two or more image sensor arrays.

Electronic camera having multiple sensors for capturing high dynamic range images and related methods

The scanning of 3D geometry has become a popular way of capturing the shape of real-world objects. Transparent objects, however, pose problems for traditional scanning methods. We present a visible light tomographic reconstruction method for recovering the shape of transparent objects, such as glass. Our setup is relatively simple to implement, and accounts for refraction, which can be a significant problem in visible light tomography.

/pdf/tomographic-reconstruction-of-transparent-objects-1hgwtph1jm.pdf

Tomographic reconstruction of transparent objects

Recent years have seen an increased interest in motion capture systems. Current systems, however, are limitedto only a few degrees of freedom, so that effectively only the motion of linked rigid bodies can be acquired. Wepresent a system for the capture of deformable surfaces, most notably moving cloth, including both geometry andparameterisation. We recover geometry using stereo correspondence, and use the Scale Invariant Feature Transform(SIFT) to identify an arbitrary pattern printed on the cloth, even in the presence of fast motion. We describea novel seed-and-grow approach to adapt the SIFT algorithm to deformable geometry. Finally, we interpolatefeature points to parameterise the complete geometry.



Categories and Subject Descriptors (according to ACM CCS): I.3.5 [Computer Graphics]: Physically based modelingI.4.8 [Image Processing and Computer Vision]: Scene analysis

Cloth Motion Capture

We present an end-to-end image processing framework for time-of-flight (ToF) cameras. Existing ToF image processing pipelines consist of a sequence of operations including modulated exposures, denoising, phase unwrapping and multipath interference correction. While this cascaded modular design offers several benefits, such as closed-form solutions and power-efficient processing, it also suffers from error accumulation and information loss as each module can only observe the output from its direct predecessor, resulting in erroneous depth estimates. We depart from a conventional pipeline model and propose a deep convolutional neural network architecture that recovers scene depth directly from dual-frequency, raw ToF correlation measurements. To train this network, we simulate ToF images for a variety of scenes using a time-resolved renderer, devise depth-specific losses, and apply normalization and augmentation strategies to generalize this model to real captures. We demonstrate that the proposed network can efficiently exploit the spatio-temporal structures of ToF frequency measurements, and validate the performance of the joint multipath removal, denoising and phase unwrapping method on a wide range of challenging scenes.

/pdf/deep-end-to-end-time-of-flight-imaging-3v2t0g6n1z.pdf

Wolfgang Heidrich

Papers

Imaging in scattering media using correlation image sensors and sparse convolutional coding

Electronic camera having multiple sensors for capturing high dynamic range images and related methods

Tomographic reconstruction of transparent objects

Cloth Motion Capture

Deep End-to-End Time-of-Flight Imaging