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.

Capturing and rendering an image that fulfills the observer's expectations is a difficult task. This is due to the fact that the signal reaching the eye is processed by a complex mechanism before forming a percept, whereas a capturing device only retains the physical value of light intensities. It is especially difficult to render complex scenes with highly varying luminances. For example, a picture taken inside a room where objects are visible through the windows will not be rendered correctly by a global

Dynamic textures are sequences of images showing temporal regularity; they can be found in videos representing smoke, flames, flowing water, or moving grass, for instance. Recently, one method based on linear dynamic system theory was proposed to synthesize dynamic textures. Textures are represented as the output of a linear dynamic system and synthesis is reduced to matrix multiplication operations. In this report, we study the problem of implementing this method using fixed-point arithmetic, as required i

We present a framework to incorporate near-infrared (NIR) information into algorithms to better segment objects by isolating material boundaries from color and shadow edges. Most segmentation algorithms assign individual regions to parts of the object that ...

Deep convolutional neural networks (CNNs), trained on corresponding pairs of high- and low-resolution images, achieve state-of-the-art performance in single-image super- resolution and surpass previous signal-processing based approaches. However, their per ...

There is an analogy between one-chip CCD cameras and the human visual system in that these two systems acquire only one wavelength sensitivity band per spatial location. We have exploited this analogy, defining a model that characterizes a one-color per spatial position image as a coding into luminance and chrominance of the corresponding three-colors per spatial position image. Luminance is defined with full spatial resolution while chrominance contains sub-sampled opponent colors. Moreover, luminance and

We propose a new method for color demosaicing based on a mathematical model of spatial multiplexing of color. We demonstrate that a one-color per pixel image can be written as the sum of luminance and chrominance. In case of a regular arrangement of colors, such as with the Bayer color filter array (CFA), luminance and chrominance are well localized in the spatial frequency domain. Our algorithm is based on selecting the luminance and chrominance signal in the Fourier domain. This simple and efficient algor

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

This paper describes the specifications and usage of standard RGB color spaces promoted today by standard bodies and/or the imaging industry. As in the past, most of the new standard RGB color spaces were developed for specific imaging workflow and applications. They are used as interchange spaces to communicate color and/or as working spaces in imaging applications. Standard color spaces can facilitate color communication: if an image is in ‘knownRGB,’ the user, application, and/or device can unambiguously

Current digital camera sensors are inherently sensitive to the near-infrared part of the spectrum. To prevent the near-IR contamination of images, an IR blocking filter (hot mirror) is placed in front of the sensor. In this work, we start by replacing the ...

Selecting cosmetics requires visual information and often benefits from the assessments of a cosmetics expert. In this paper we present a unique mobile imaging application that enables women to use their cell phones to get immediate expert advice when sele ...

We propose a compression framework for four-channel images, composed of color (RGB) and near-infrared (NIR) channels, which exploits the correlation between the visible and the NIR information. The high-frequency components of both visible and NIR scene re ...

Various computer visions tasks require a summary of visually important regions in an image. Thus, developing simple yet accurate salient region detection algorithms has become an important research topic. The currently best performing state-of-the-art sali ...

We study a new image device called gigavision camera or the gigapixel digital film camera. The main differences between a conventional and a gigavision camera are that the pixels of the latter are binary and orders of magnitude smaller. A gigavision camera can be built using standard memory chip technology, where each memory bit is designed to be light sensitive. A conventional gray level image can be obtained from the binary gigavision image by low-pass filtering and sampling. The main advantage of the gig

We introduce Neural Particle Automata (NPA), a Lagrangian generalization of Neural Cellular Automata (NCA) from static lattices to dynamic particle systems. Unlike classical Eulerian NCA where cells are fixed to pixels or voxels, NPA represent each cell as a particle with a continuous position and an internal state, both updated by a shared learnable neural rule. This particle-based formulation yields clear individuation of cells, allows heterogeneous dynamics, and focuses computation on regions where activ

Fast and accurate salient-object detectors are important for various image processing and computer vision applications, such as adaptive compression and object segmentation. It is also desirable to have a detector that is aware of the position and the size ...

Neural Cellular Automata (NCAs) are bio-inspired dynamical systems in which identical cells iteratively apply a learned local update rule to self-organize into complex patterns, exhibiting regeneration, robustness, and spontaneous dynamics. Despite their success in texture synthesis and morphogenesis, NCAs remain largely confined to low-resolution outputs. This limitation stems from (1) training time and memory requirements that grow quadratically with grid size, (2) the strictly local propagation of inform

The present invention concerns a method of classifying a media item into a user profile suitability class in a classification system comprising a set of pre-trained artificial neural networks. The method comprising: receiving (101) a media file; extracting ...

Image optimization problems encompass many applications such as spectral fusion, deblurring, deconvolution, dehazing, matting, reflection removal and image interpolation, among others. With current image sizes in the order of megabytes, it is extremely exp ...

We investigated the spectral properties of color detection mechanisms via a noise masking paradigm. Contrast detection thresholds were measured for equiluminant chromatic modulations in the (L-M,S-(L+M))-plane within a random texture. Each texture image was the spatial juxtaposition of color samples drawn from a bi-dimensional probability density function whose support was a sector in the equiluminant plane. The task consisted in the detection of an equiluminant signal of Gaussian shape (sigma = 1.25 deg) w

Color deficient individuals have trouble seeing color contrasts that could be very apparent to individuals with normal color vision. For example, for some color deficient individuals, red and green apples do not have the striking contrast they have for those with normal color vision, or the abundance of red cherries in a tree is not immediately clear due to a lack of perceived contrast. We present a smartphone app that enables color deficient users to visualize such problematic color contrasts in order to h

Sabine Süsstrunk

Chat with Graph Search

Bio-inspired image enhancement for natural color images

Dynamic Texture on Fixed-Point Architectures

Material-Based Object Segmentation Using Near-Infrared Information

Kernel Modeling Super-Resolution on Real Low-Resolution Images

Accurate Color Demosaicing inspired by the Human Visual System

Color Demosaicing by Estimating Luminance and Opponent Chromatic Signals in the Fourier Domain

Assessing human skin color from uncalibrated images

Standard RGB Color Spaces

Colouring the near infrared

Mobile Cosmetics Advisor: An Imaging Based Mobile Service

Compression of Multispectral Images: Color (RGB) plus Near-Infrared (NIR)

Low-Level Salient Region Detection Using Multi-Scale Filtering

The Gigavision Camera

Neural Particle Automata: Learning Self-Organizing Particle Dynamics

FASA: Fast, Accurate, and Size-Aware Salient Object Detection

Neural Cellular Automata: From Cells to Pixels

Dynamic media content categorisation method

Fourier-Domain Optimization for Image Processing

Spectral Bandwidths for the Detection of Colour within Random Colour Textures

An Interactive App for Color Deficient Viewers