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.

We present a method to calculate sets of RGB primaries that are white-point independent and have suitable gamut properties when evaluated with regards to surface colors. These primaries can be used as a basis for defining an output-referred color encoding intended for print applications. The resulting RGB sensors are sharp, i.e. decorrelated, emphasizing again that for imaging applications, the choice of a chromatic adaptation transform based on sharp sensors might be most appropriate.

Detection of salient image regions is useful for applications like image segmentation, adaptive compression, and region-based image retrieval. In this paper we present a novel method to determine salient regions in images using low-level features of lumina ...

Image classification has significantly improved using deep learning. This is mainly due to convolutional neural networks (CNNs) that are capable of learning rich feature extractors from large datasets. However, most deep learning classification methods are ...

Shadows often introduce errors in the performance of computer vision algorithms, such as object detection and tracking. This paper proposes a method to remove shadows from real images based on a probability shadow map. The probability shadow map identifies ...

We present a method for synthesizing high reliefs, a sculpting technique that attaches 3D objects onto a 2D surface within a limited depth range. The main challenges are the preservation of distinct scene parts by preserving depth discontinuities, the fine ...

The currently best performing state-of-the-art saliency detection algorithms incorporate heuristic functions to evaluate saliency. They require parameter tuning, and the relationship between the parameter value and visual saliency is often not well underst ...

Clinical applications, such as image-guided surgery and noninvasive diagnosis, rely heavily on multi-modal images. Medical image fusion plays a central role by integrating information from multiple sources into a single, more understandable output. We prop ...

Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person’s expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Som ...

We propose a complete digital camera workflow to capture and render high dynamic range (HDR) static scenes, from RAW sensor data to an output- referred encoded image. In traditional digital camera processing, demosaicing is one of the first operations done ...

Blind and universal image denoising consists of using 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-gr ...

The color-appearance model CIECAM02 has several problems, which can result in mathematical instabilities, due to the relation of the chromatic-adaptation primaries to the spectrum locus and to the presumed physiological cone primaries. To keep a correspond ...

There are a number of color encoding standards that have lately been developed ant are being proposed to the imaging community for different encoding steps in the color imaging workflow, optimized for different purposes. In this paper, their applicability for master and derivative image file encoding for image databases is discussed. Several types of image databases are defined, and the advantages and disadvantages of archiving master files after different image workflow steps are outlined. Several input- a

Multimedia data with associated semantics is omnipresent in today’s social online platforms in the form of keywords, user comments and so forth. This article presents a statistical framework designed to infer knowledge in the imaging domain from the semant ...

There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate that this signa ...

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 th ...

We present a novel framework for automatically determining whether or not to apply black point compensation (BPC) in image reproduction. Visually salient objects have a larger influence on determining image quality than the number of dark pixels in an image, and thus should drive the use of BPC. We propose a simple and efficient algorithmic implementation to determine when to apply BPC based on low-level saliency estimation. We evaluate our algorithm with a psychophysical experiment on an image data set pri

Digitally, panoramic pictures can be assembled from several individual, overlapping photographs. While the geometric alignment of these photographs has retained a lot of attention from the computer vision community, the mapping of colour, i.e. the correction of colour mismatches, has not been studied extensively. In this article, we analyze the colour rendering of today’s digital photographic systems, and propose a method to correct for colour differences. The colour correction consists in retrieving linear

Image relighting is attracting increasing interest due to its various applications. From a research perspective, image relighting can be exploited to conduct both image normalization for domain adaptation, and also for data augmentation. It also has multip ...

State of the art content-based image retrieval algorithms owe their excellent performance to the rich semantics encoded in the deep activations of a convolutional neural network. The difference between these algorithms lies mostly in how activations are co ...

Developing an augmented reality (AR) system involves a multitude of interconnected algorithms such as image fusion, camera synchronization and calibration, and brightness control, each having diverse parameters. This abundance of features, while beneficial ...

Sabine Süsstrunk

Chat with Graph Search

White-Point Independant RGB Primaries for Color Image Encoding

Salient Region Detection and Segmentation

Fidelity Estimation Improves Noisy-Image Classification with Pretrained Networks

Removing Shadows from Images Using Color and Near-infrared

High Relief from 3D Scenes

Saliency Detection Using Regression Trees on Hierarchical Image Segments

Zero-Learning Fast Medical Image Fusion

Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors

Digital Camera Workflow for High Dynamic Range Images Using a Model of Retinal Processing

Blind Universal Bayesian Image Denoising With Gaussian Noise Level Learning

Repairing Gamut Problems in CIECAM02: A Progress Report

Color Encodings for Image Databases

Semantic-Improved Color Imaging Applications: It Is All About Context

Exploiting the Signal-Leak Bias in Diffusion Models

TempSAL - Uncovering Temporal Information for Deep Saliency Prediction

Saliency-driven Black Point Compensation

Mapping colour in image stitching applications

NTIRE 2021 Depth Guided Image Relighting Challenge

Deep Feature Factorization For Content-Based Image Retrieval And Localization

AR in VR: Simulating augmented reality glass for image fusion