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.

A cost-effective and convenient approach for color imaging is to use a single sensor and mount a color filter array (CFA) in front of it, such that at each spatial position the scene information in only one color channel is captured. To estimate the missin ...

Content aware image re-targeting methods aim to arbitrarily change image aspect ratios while preserving visually prominent features. To determine visual importance of pixels, existing re-targeting schemes mostly rely on grayscale intensity gradient maps. T ...

We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images. We use DFF to gain insight into a deep convolutional neural network's learned features, where we detect hierarchical c ...

We present a study of the in-camera image processing through an extensive analysis of more than 10,000 images from over 30 cameras. The goal of this work is to investigate if image values can be transformed to physically meaningful values, and if so, when ...

Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information, such as scene context, semantic relationships, gaze direction, and object dissimilarity. However, none of these models consider the temporal nature of gaze shifts during image observation. We introduce a novel saliency prediction model that learns to output saliency maps in sequential time intervals by exploiting human temporal attention patterns. Our approach locally modulates the

The slowing down of Moore's law and the emergence of new technologies puts an increasing pressure on the field of EDA. There is a constant need to improve optimization algorithms. However, finding and implementing such algorithms is a difficult task, espec ...

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 process. We propose Dynamic Neural Cellular Automata (DyNCA), a framework for real-time and controllable dynamic texture synthesis. Our method is built upon the recently introduced NCA models and can synthesize infinitely long and arbitrary-sized realistic

Computer vision applications are able to model and reconstruct three dimensional scenes from several pictures. In this work, we are interested in the group of algorithm that register each image with respect to the model and aim at constructing a model of the scene. At the lowest level, most of these algorithms are comparing the pixel values of the image to the ones predicted by the model to refine the result. As research advances, the models are getting better and better, but no matter how complex they are,

We present a new adaptation of Retinex to enhance the rendering of high dynamic range digital color images. The image is processed using an adaptive Gaussian filter. The shape of the filter basis is adapted to follow the high contrasted edges of the image. In this way, the artifacts introduced by a circularly symmetric filter at the border of high contrasted areas are reduced. This method provides a way of rendering natural images that is inspired by human local adaptation. It is included into a framework t

Nowadays, the ability to create panoramic photographs is included with most of the commercial digital cameras. The principle is to shoot several pictures and stitch them together to build a panorama. To ensure the quality of the final image, the different pictures have to be perfectly aligned and the colors of the images should match. While the alignment of images has received a lot of attention from the computer vision community, the mismatch in colors was often ignored and handled using smooth transitions

We present a method to train self-binarizing neural networks, that is, networks that evolve their weights and activations during training to become binary. To obtain similar binary networks, existing methods rely on the sign activation function. This function, however, has no gradients for non-zero values, which makes standard backpropagation impossible. To circumvent the difficulty of training a network relying on the sign activation function, these methods alternate between floating-point and binary repre

We address the question of how to characterize the outliers that may appear when matching two views of the same scene. The match is performed by comparing the difference of the two views at a pixel level, aiming at a better registration of the images. When using digital photographs as input, we notice that an outlier is often a region that has been occluded, an object that suddenly appears in one of the images, or a region that undergoes an unexpected motion. By assuming that the error in pixel intensity le

Many algorithms have been proposed to solve the problem of matching feature points in two or more images using geometric assumptions to increase the robustness of the matching. However, these assumptions do not always hold; in particular, few methods addre ...

Recent progress in computational photography has shown that we can acquire physical information beyond visible (RGB) image representations. In particular, we can acquire near-infrared (NIR) cues with only slight modification to any standard digital camera. ...

There are many works in colour that assume illumination change can be modelled by multiplying sensor responses by individual scaling factors. The early research in this area are sometimes grouped under the heading von Kries adaptation: the scaling factors ...

We want to integrate colourfulness in an image quality evaluation framework. This quality framework is meant to evaluate the perceptual impact of a compression algorithm or an error prone communication channel on the quality of an image. The image might go through various enhancement or compression algorithms, resulting in a different -- but not necessarily worse -- image. In other words, we will measure quality but not fidelity to the original picture.While modern colour appearance models are able to predi

Vision Transformers (ViTs) demonstrate remarkable performance in image classification through visual-token interaction learning, particularly when equipped with local information via region attention or convolutions. Although such architectures improve the ...

We present a method to automatically detect dust and scratches on photographic material, in particular silver halide film, where traditional methods for detecting and removing defects fail. The film is digitized using a novel setup involving crosspolarizat ...

Robustness to adversarial attacks was shown to require a larger model capacity, and thus a larger memory footprint. In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks. Unlike adversar ...

We study the influence of the choice of color space for local tone mapping methods. Many local tone mapping methods do not perform well when applied independently to the three color channels of an RGB image. A common solution is to only treat the luminance ...

Sabine Süsstrunk

Chat with Graph Search

Optimum Spectral Sensitivity Functions for Single Sensor Color Imaging

Saliency Detection for Content-aware Image Resizing

Deep Feature Factorization for Concept Discovery

A New In-Camera Imaging Model for Color Computer Vision and its Application

TempSAL - Uncovering Temporal Information for Deep Saliency Prediction

Deep Learning for Logic Optimization Algorithms

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

Using colour to model outliers

Color image enhancement using a Retinex-based adaptive filter

Color Handling in Panoramic Photography

Self-Binarizing Networks

Outlier modeling in image matching

Mirror Match: Reliable Feature Point Matching Without Geometric Constraints

Semantic Image Segmentation Using Visible and Near-Infrared Channels

Spectral Sharpening by Spherical Sampling

Measuring Colourfulness in Natural Images

AdaNCA: Neural Cellular Automata as Adaptors for More Robust Vision Transformer

Automatic Detection of Dust and Scratches in Silver Halide Film using Polarized Dark-Field Illumination

Robust Binary Models by Pruning Randomly-initialized Networks

The Influence of Luminance on Local Tone Mapping