Publications by Sabine Süsstrunk

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

The Bradford chromatic adaptation transform, empirically derived by Lam, models illumination change. Specifically, it pro-vides a means of mapping XYZs under a reference light source to XYZs for a target light source such that the corresponding XYZs produce the same perceived color. One implication of the Bradford chromatic adaptation transform is that color correction for illumination takes place not in cone space but rather in a ‘narrowed’ cone space. The Bradford sensors have their sensitivity more narro

Images of a scene captured with multiple cameras will have different color values due to variations in capture and color rendering across devices. We present a method to accurately retrieve color information from uncalibrated images taken under uncontrolle ...

In fluorescence microscopy live-cell imaging, there is a critical trade-off between the signal-to-noise ratio and spatial resolution on one side, and the integrity of the biological sample on the other side. To obtain clean high-resolution (HR) images, one ...

Random textures differ from natural textures because they lack structure. Structure is a concept that is difficult to formalize, however, we generally observe that it is associated to spatial dependency between adjacent pixels. Random textures, in fact, are characterized by independent pixels, while natural textures show some local dependencies. In this paper, we propose a measure for this local dependency. We find the minimal distance between pixels that ensures spatial independence. We assume that this di

Despite the advances in single-image super resolution using deep convolutional networks, the main problem remains unsolved: recovering fine texture details. Recent works in super resolution aim at modifying the training of neural networks to enable the rec ...

We analyze the influence of adversarial training on the loss landscape of machine learning models. To this end, we first provide analytical studies of the properties of adversarial loss functions under different adversarial budgets. We then demonstrate tha ...

Existing techniques to encode spatial invariance within deep convolutional neural networks (CNNs) apply the same warping field to all the feature channels. This does not account for the fact that the individual feature channels can represent different sema ...

Permanence issues for digital photographs arise in three different areas. First, the materials used for digital hard copies should preferably be as permanent as the conventional photographic materials. Longevity of digital hard copy materials is affected by the stability of the material and the storage conditions. Secondly, the digital files that are the counterpart of the conventional negatives need to be readable not only on various systems and platforms today but also in the future. Third, the encoding o

The present invention concerns a method of displaying an image on a see-through display. The method comprises: obtaining (101) a first electromagnetic radiation matrix of an object, the first matrix comprising first matrix elements representing radiation i ...

Shadows, due to their prevalence in natural images, are a long studied phenomenon in digital photography and computer vision. Indeed, their presence can be a hindrance for a number of algorithms; accurate detection (and sometimes subsequent removal) of shadows in images is thus of paramount importance. In this paper, we present a method to detect shadows in a fast and accurate manner. To do so, we employ the inherent sensitivity of digital camera sensors to the near-infrared (NIR) part of the spectrum. We s

In this paper, we present a super-resolution method to approximately double image resolution in both dimensions from a set of four low resolution, aliased images. The camera is shifted and rotated by small amounts between the different image captures. Only the low frequency, aliasing-free part of the images is used to find the shift and rotation parameters. When the images are registered, it is possible to reconstruct a higher resolution, aliasing-free image from the four low resolution images using cubic i

We present a color thesaurus with over 9000 color names in ten different languages. Instead of using conventional psychophysical experiments, we use a statistical framework that is based on search results from Google Image Search. For each color name we co ...

We address the problem of stably and efficiently training a deep neural network robust to adversarial perturbations bounded by an

l_1

norm. We demonstrate that achieving robustness against

l_1

-bounded perturbations is more challenging than in the

l_2

...

In this paper, we present a simple method to almost quadruple the spatial resolution of aliased images. From a set of four low resolution, undersampled and shifted images, a new image is constructed with almost twice the resolution in each dimension. The resulting image is aliasing-free. A small aliasing-free part of the frequency domain of the images is used to compute the exact subpixel shifts. When the relative image positions are known, a higher resolution image can be constructed using the Papoulis-Ger

We present a method for hiding images in synthetic videos and reveal them by temporal averaging. We developed a visual masking method that hides the input image both spatially and temporally. Our masking approach consists of temporal and spatial pixel by p ...

Chromatic adaptation transforms are used in imaging system to map image appearance to colorimetry under different illumination sources. In this paper, the performance of different chromatic adaptation transforms (CAT) is compared with the performance of transforms based on RGB primaries that have been investigated in relation to standard color spaces for digital still camera characterization and image interchange. The chromatic adaptation transforms studied are von Kries, Bradford, Sharp, and CMCCAT2000. Th

This paper presents a novel method of enhancing image quality of face pictures using 3D and spectral information. Most conventional techniques directly work on the image data, shifting the skin color to a predefined skin tone, and so do not take into accou ...

We propose a new image device called gigavision camera. The main differences between a conventional and a gigavision camera are that the pixels of the gigavision camera are binary and orders of magnitude smaller. A gigavision camera can be built using stan ...

We present a virtual digital camera sensor, whose aim is to simulate a real (physical) image capturing sensor.To accomplish this task, the virtual sensor operates in two steps. First, it accepts a physical description of agiven scene and simulates the entire process of photon sensing and charge generation in the sensor device. This process is affected by noise, mostly photon noise. Second, it adds to the image the noise that results from the electronic circuitry. We present a model for the different sources

Current Dynamic Texture Synthesis (DyTS) models can synthesize realistic videos. However, they require a slow iterative optimization process to synthesize a single fixed-size short video, and they do not offer any post-training control over the synthesis p ...

Sabine Süsstrunk

Chat with Graph Search

Performance of a Chromatic Adaptation Transform Based on Spectral Sharpening

Color correction of uncalibrated images for the classification of human skin color

W2S: Microscopy Data with Joint Denoising and Super-Resolution for Widefield to SIM Mapping

A Measure For Spatial Dependency In Natural Stochastic Textures

A comparative study on wavelets and residuals in deep super resolution

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

Volumetric Transformer Networks

Digital Photography - How Long Will It Last

Method of displaying an image on a see-through display

Automatic and accurate shadow detection from (potentially) a single image using near-infrared information

Double resolution from a set of aliased images

A Large-Scale Multi-Lingual Color Thesaurus

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Superresolution images reconstructed from aliased images

Synthetic electronic video containing a hidden image

Chromatic adaptation performance of different RGB sensors

Face Image Enhancement Using 3D and Spectral Information

The Gigavision Camera

Virtual Sensor Design

DyNCA: Real-time Dynamic Texture Synthesis Using Neural Cellular Automata