Publications by Sabine Süsstrunk

Related publications (187)

Evaluating salient object detection in natural images with multiple objects having multi-level saliency

Salient object detection is evaluated using binary ground truth (GT) with the labels being salient object class and background. In this study, the authors corroborate based on three subjective experiments on a novel image dataset that objects in natural im ...

2020

Mesh Neural Cellular Automata

Sabine Süsstrunk, Tong Zhang, Ehsan Pajouheshgar, Yitao Xu

Texture modeling and synthesis are essential for enhancing the realism of virtual environments. Methods that directly synthesize textures in 3D offer distinct advantages to the UV-mapping-based methods as they can create seamless textures and align more cl ...

Association for Computing Machinery (ACM)2024

NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata

Sabine Süsstrunk, Ehsan Pajouheshgar, Yitao Xu

Neural Cellular Automata (NCA) is a class of Cellular Automata where the update rule is parameterized by a neural network that can be trained using gradient descent. In this paper, we focus on NCA models used for texture synthesis, where the update rule is ...

MIT Press2024

Automatic Skin Enhancement with Visible and Near-Infrared Image Fusion

Sabine Süsstrunk

Skin tones, portraits in particular, are of critical importance in photography and video, but a number of factors, such as pigmentation irregularities (e.g., moles, freckles), irritation, roughness, or wrinkles can reduce their appeal. Moreover, such “defe ...

2010

Saliency prediction in 360° architectural scenes: Performance and impact of daylight variations

Marilyne Andersen, Sabine Süsstrunk, Caroline Karmann, Kynthia Chamilothori, Seungryong Kim, Bahar Aydemir

Saliency models are image-based prediction models that estimate human visual attention. Such models, when applied to architectural spaces, could pave the way for design decisions where visual attention is taken into account. In this study, we tested the pe ...

2023

Tone Mapping For High Dynamic Range Displays

Sabine Süsstrunk, Laurence Meylan

We address the problem of re-rendering images to high dynamic range (HDR) displays, which were originally tone-mapped to standard displays. As these new HDR displays have a much larger dynamic range than standard displays, an image rendered to standard mon ...

2007

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising

Liying Lu, Raphaël Wan-Li Marc Achddou, Sabine Süsstrunk

Low-light photography produces images with low signal-to-noise ratios due to limited photons. In such conditions, common approximations like the Gaussian noise model fall short, and many denoising techniques fail to remove noise effectively. Although deep- ...

2025

Demultiplexing Visible and Near-Infrared Information in Single- Sensor Multispectral Imaging

Sabine Süsstrunk, Zahra Sadeghipoor Kermani

In this paper, we study a single-sensor imaging system that uses a multispectral filter array to spectrally sample the scene. Our system captures information in both visible and near-infrared bands of the electromagnetic spectrum. Due to manufacturing limi ...

2016

A Model of Retinal Local Adaptation for the Tone Mapping of Color Filter Array Images

Sabine Süsstrunk, Laurence Meylan

We present a tone mapping algorithm that is derived from a model of retinal processing. Our approach has two major improvements over existing methods. First, tone mapping is applied directly on the mosaic image captured by the sensor, analogue to the human ...

2007

Illuminant estimation and detection using near infrared

Sabine Süsstrunk

Digital camera sensors are sensitive to wavelengths ranging from the ultraviolet (200-400nm) to the near-infrared (700-100nm) bands. This range is, however, reduced because the aim of photographic cameras is to capture and reproduce the visible spectrum (4 ...

2009

Training Provably Robust Models by Polyhedral Envelope Regularization

Sabine Süsstrunk, Mathieu Salzmann, Chen Liu

Training certifiable neural networks enables us to obtain models with robustness guarantees against adversarial attacks. In this work, we introduce a framework to obtain a provable adversarial-free region in the neighborhood of the input data by a polyhedr ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

A Novel Compressive Sensing Approach to Simultaneously Acquire Color and Near-infrared Images on a Single Sensor

Sabine Süsstrunk, Yue Lu, Zahra Sadeghipoor Kermani

Sensors of most digital cameras are made of silicon that is inherently sensitive to both the visible and near-infrared parts of the electromagnetic spectrum. In this paper, we address the problem of color and NIR joint acquisition. We propose a framework f ...

2013

Higher Order SVD Analysis for Dynamic Texture Synthesis

Sabine Süsstrunk, Luciano Sbaiz, Roberto Costantini

Videos representing flames, water, smoke, etc. are often defined as dynamic textures: "textures" because they are characterized by redundant repetition of a pattern and "dynamic" because this repetition is also in time and not only in space. Dynamic textur ...

Institute of Electrical and Electronics Engineers2008

Deep Semantic Segmentation Using Nir As Extra Physical Information

Sabine Süsstrunk, Siavash Arjomand Bigdeli

Deep neural networks for semantic segmentation are most often trained with RGB color images, which encode the radiation visible to the human eyes. In this paper, we study if additional physical scene information, specifically Near-Infrared (NIR) images, im ...

IEEE2019

Preserving Perceptual Contrast in Decolorization with Optimized Color Orders

Sabine Süsstrunk, Bin Jin

Converting a color image to a grayscale image, namely decolorization, is an important process for many real-world applications. Previous methods build contrast loss functions to minimize the contrast differences between the color images and the resultant g ...

2017

Multiscale guided deblurring: Chromatic aberration correction in color and near-infrared imaging

Sabine Süsstrunk, Yue Lu, Zahra Sadeghipoor Kermani

Chromatic aberration, caused by photographic lens imperfections, results in the image of only one spectral channel being sharp, while the other channels are blurred depending on their wavelengths difference with the sharp channel. We study chromatic aberra ...

2015

Dense Multitask Learning to Reconfigure Comics

Sabine Süsstrunk, Mathieu Salzmann, Deblina Bhattacharjee

In this paper, we develop a MultiTask Learning (MTL) model to achieve dense predictions for comic panels to, in turn, facilitate the transfer of comics from one publication channel to another by assisting authors in the task of reconfiguring their narrativ ...

IEEE2023

Color Image Dehazing using the Near-Infrared

Sabine Süsstrunk

In landscape photography, distant objects often appear blurred with a blue color cast, a degradation caused by atmospheric haze. To enhance image contrast, pleasantness and information content, dehazing can be performed. We propose that fusing a visible an ...

2009

Material-Based Object Segmentation Using Near-Infrared Information

Sabine Süsstrunk, Neda Salamati

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 ...

2010

Kernel Modeling Super-Resolution on Real Low-Resolution Images

Sabine Süsstrunk, Ruofan Zhou

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 ...

IEEE COMPUTER SOC2019