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.

In this paper, we present a spherical sampling technique that can be employed to find optimal sensors for trichromatic color applications. The advantage over other optimization techniques is that it assures a global minimum is found, and that not only one, but a set of solutions is retained if so desired. The sampling technique is used to find all possible RGB sensors that exhibit favorable chromatic adaptation transform (CAT) behavior when tested on Lam’s corresponding color data set, subject to a CIE Delt

Digital camera sensors are inherently sensitive to the near-infrared (NIR) part of the light spectrum. In this paper, we propose a general design for color filter arrays that allow the joint capture of visible/NIR images using a single sensor. We pose the ...

Designing aesthetically pleasing and challenging jigsaw puzzles is considered an art that requires considerable skill and expertise. We propose a tool that allows novice users to create customized jigsaw puzzles based on the image content and a user-define ...

Saliency prediction has made great strides over the past two decades, with current techniques modeling low-level information, such as color, intensity and size contrasts, and high-level ones, such as attention and gaze direction for entire objects. Despite ...

We present a new algorithm that performs demosaicing and super-resolution jointly from a set of raw images sampled with a color filter array. Such a combined approach allows us to compute the alignment parameters between the images on the raw camera data b ...

Size uniformity is one of the prominent features of superpixels. However, size uniformity rarely conforms to the varying content of an image. The chosen size of the superpixels therefore represents a compromise - how to obtain the fewest superpixels withou ...

An online memory matching game is used to explore the collective performance for stimulus sets varying in color, text and texture. The game is a consistent five wide by four high array of 70 by 70 pixels squares for a total of eleven unique test pairs. Use ...

In this paper, we describe the Perceptual Image Restoration and Manipulation (PIRM) workshop challenge on spectral image super- resolution, motivate its structure and conclude on results obtained by the participants. The challenge is one of the first of its kind, aiming at leveraging modern machine learning techniques to achieve spectral image super-resolution. It comprises of two tracks. The first of these (Track 1) is about example-based single spectral image super-resolution. The second one (Track 2) is

In this paper, color encoding strategies for different image database applications are discussed. The color image workflow is examined in detail, and master and derivative file encoding strategies are outlined in relation to capture, maintenance, and deployment of image files. For the most common image database purposes, recommendations are given as to which type of color encoding is most suitable. Advantages and disadvantages of sensor, input-referred, output-referred, and output device specific color enco

We use a simple modification to a conventional SLR camera to capture images of several hundred scenes in colour (RGB) and near-infrared (NIR). We show that the addition of near-infrared information leads to significantly improved performance in a scene-rec ...

In this paper, the performance of chromatic adaptation transforms based on stable color ratios is investigated.It was found that for three different sets of reflectance data, their performance was not statistically different from CMCCAT2000,when applying the chromatic adaptation transforms to Lam’s corresponding color data set and using a perceptual error metric of CIE Delta E94.The sensors with the best color ratio stability are much sharper and more de-correlated than the CMCCAT2000 sensors, corresponding

Memory colours refer to the colour of specific image classes that have the essential attribute of being perceived in a consistent manner by human observers. In colour correction or rendering tasks, this consistency implies that they have to be faithfully r ...

This work presents a framework for image classification based on region information. The main application of this framework is for automatic color correction of real-scene images. Class specific color correction is already implemented in some systems, but image classification usually relies on global image features only. Our region-based approach shows a significant improvement over previously achieved classification for a variety of critical image classes. Improved image classification can directly be tran

Super-resolution and denoising are ill-posed yet fundamental image restoration tasks. In blind settings, the degradation kernel or the noise level are unknown. This makes restoration even more challenging, notably for learning-based methods, as they tend t ...

Blind and universal image denoising consists of a unique model that denoises images with any level of noise. It is especially practical as noise levels do not need to be known when the model is developed or at test time. We propose a theoretically-grounded ...

Face recognition systems are designed to handle well-aligned images captured under controlled situations. However real-world images present varying orientations, expressions, and illumination conditions. Traditional face recognition algorithms perform poor ...

With the advent of social image-sharing communities, millions of images with associated semantic tags are now available online for free and allow us to exploit this abundant data in new ways. We present a fast non-parametric statistical framework designed ...

The success of the Neural Radiance Fields (NeRF) in novel view synthesis has inspired researchers to propose neural implicit scene reconstruction. However, most existing neural implicit reconstruction methods optimize perscene parameters and therefore lack ...

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

While the quality of GAN image synthesis has improved tremendously in recent years, our ability to control and condition the output is still limited. Focusing on StyleGAN, we introduce a simple and effective method for making local, semantically-aware edit ...

Sabine Süsstrunk

Chat with Graph Search

Spherical Sampling and Color Transformations

Designing color filter arrays for the joint capture of visible and near-infrared images

Creating Personalized Jigsaw Puzzles

Modeling Object Dissimilarity for Deep Saliency Prediction

Joint Demosaicing and Super-Resolution Imaging from a Set of Unregistered Aliased Images

Scale-Adaptive Superpixels

Games with Hypotheses: Color, Text and Texture

PIRM2018 Challenge on Spectral Image Super-Resolution: Methods and Results

Color Strategies for Image Databases

Multispectral SIFT for Scene Category Recognition

Color Ratios and Chromatic Adaptation

Segmenting memory colours

Region-based image classification for automatic color correction

Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks

Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning

Face Recognition in Real-world Images

Joint Statistical Analysis of Images and Keywords with Applications in Semantic Image Enhancement

VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Editing in Style: Uncovering the Local Semantics of GANs