There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Moreover, since the release of the pix2pix software associated with this paper, hundreds of twitter users have posted their own artistic experiments using our system. As a community, we no longer hand-engineer our mapping functions, and this work suggests we can achieve reasonable results without handengineering our loss functions either.

/pdf/image-to-image-translation-with-conditional-adversarial-5058t24et2.pdf

Image-to-Image Translation with Conditional Adversarial Networks

We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Indeed, since the release of the pix2pix software associated with this paper, a large number of internet users (many of them artists) have posted their own experiments with our system, further demonstrating its wide applicability and ease of adoption without the need for parameter tweaking. As a community, we no longer hand-engineer our mapping functions, and this work suggests we can achieve reasonable results without hand-engineering our loss functions either.

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

Importance Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. Objective Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin–stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists’ diagnoses in a diagnostic setting. Design, Setting, and Participants Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). Exposures Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. Main Outcomes and Measures The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. Results The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884];P  Conclusions and Relevance In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.

/pdf/diagnostic-assessment-of-deep-learning-algorithms-for-13rg5habe2.pdf

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer.

We use a simple statistical analysis to impose one image's color characteristics on another. We can achieve color correction by choosing an appropriate source image and apply its characteristic to another image.

https://www.cs.tau.ac.il/~turkel/imagepapers/ColorTransfer.pdf

Color transfer between images

A classic photographic task is the mapping of the potentially high dynamic range of real world luminances to the low dynamic range of the photographic print. This tone reproduction problem is also faced by computer graphics practitioners who map digital images to a low dynamic range print or screen. The work presented in this paper leverages the time-tested techniques of photographic practice to develop a new tone reproduction operator. In particular, we use and extend the techniques developed by Ansel Adams to deal with digital images. The resulting algorithm is simple and produces good results for a wide variety of images.

/pdf/photographic-tone-reproduction-for-digital-images-k89wmpv97f.pdf

Photographic tone reproduction for digital images

Foreword Preface 1 Introduction 2 Light And Color 3 HDR Image Encodings 4 HDR Image Capture 5 Display Devices 6 The Human Visual System and HDR Tone Mapping 7 Spatial Tone Reproduction 8 Frequency Domain and Gradient Domain Tone Reproduction 9 Image-Based Lighting List of Symbols References Index

High Dynamic Range Imaging: Acquisition, Display, and Image-Based Lighting

This landmark book is the first to describe HDRI technology in its entirety and covers a wide-range of topics, from capture devices to tone reproduction and image-based lighting. The techniques described enable you to produce images that have a dynamic range much closer to that found in the real world, leading to an unparalleled visual experience. As both an introduction to the field and an authoritative technical reference, it is essential to anyone working with images, whether in computer graphics, film, video, photography, or lighting design.



New material includes chapters on High Dynamic Range Video Encoding, High Dynamic Range Image Encoding, and High Dynammic Range Display Devices
Written by the inventors and initial implementors of High Dynamic Range Imaging
Covers the basic concepts (including just enough about human vision to explain why HDR images are necessary), image capture, image encoding, file formats, display techniques, tone mapping for lower dynamic range display, and the use of HDR images and calculations in 3D rendering
Range and depth of coverage is good for the knowledgeable researcher as well as those who are just starting to learn about High Dynamic Range imaging


Table of Contents

Introduction; Light and Color; HDR Image Encodings; HDR Video Encodings; HDR Image and Video Capture; Display Devices; The Human Visual System and HDR Tone Mapping; Spatial Tone Reproduction; Frequency Domain and Gradient Domain Tone Reproduction; Inverse Tone Reproduction; Visible Difference Predictors; Image-Based Lighting.

High Dynamic Range Imaging: Acquisition, Display, and Image-Based Lighting (The Morgan Kaufmann Series in Computer Graphics)

A common task in computer graphics is the mapping of digital high dynamic range images to low dynamic range display devices such as monitors and printers. This task is similar to the adaptation processes which occur in the human visual system. Physiological evidence suggests that adaptation already occurs in the photoreceptors, leading to a straightforward model that can be easily adapted for tone reproduction. The result is a fast and practical algorithm for general use with intuitive user parameters that control intensity, contrast, and level of chromatic adaptation, respectively.

Erik Reinhard

Papers

Color transfer between images

Photographic tone reproduction for digital images

High Dynamic Range Imaging: Acquisition, Display, and Image-Based Lighting

High Dynamic Range Imaging: Acquisition, Display, and Image-Based Lighting (The Morgan Kaufmann Series in Computer Graphics)

Dynamic range reduction inspired by photoreceptor physiology