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.

Generative Adversarial Network (GAN) based localized image editing can suffer from ambiguity between semantic attributes. We thus present a novel objective function to evaluate the locality of an image edit. By introducing the supervision from a pre-traine ...

Finding accurate correspondences among different views is the Achilles’ heel of unsupervised Multi-View Stereo (MVS). Existing methods are built upon the assumption that corresponding pixels share similar photometric features. However, multi-view images in ...

Text-to-image models, such as Stable Diffusion, can generate high-quality images from simple textual prompts. With methods such as Textual Inversion, it is possible to expand the vocabulary of these models with additional concepts, by learning the vocabula ...

We propose the Subtractive Modulative Network (SMN), a novel, parameter-efficient Implicit Neural Representation (INR) architecture inspired by classical subtractive synthesis. The SMN is designed as a principled signal processing pipeline, featuring a learnable periodic activation layer (Oscillator) that generates a multi-frequency basis, and a series of modulative mask modules (Filters) that actively generate high-order harmonics. We provide both theoretical analysis and empirical validation for our desig

We propose an end-to-end Multitask Learning Transformer framework, named MulT, to simultaneously learn multiple high-level vision tasks, including depth estimation, semantic segmentation, reshading, surface normal estimation, 2D keypoint detection, and edg ...

Aliasing artifacts in images are visually very disturbing. Therefore, most imaging devices apply a low-pass filter before sampling. This removes all aliasing from the image, but it also creates a blurred image. Actually, all the image information above hal ...

Deep image relighting is gaining more interest lately, as it allows photo enhancement through illumination-specific retouching without human effort. Aside from aesthetic enhancement and photo montage, image relighting is valuable for domain adaptation, whether to augment datasets for training or to normalize input test data. Accurate relighting is, however, very challenging for various reasons, such as the difficulty in removing and recasting shadows and the modeling of different surfaces. We present a nove

For certain databases and classification tasks, analyzing images based on region features instead of image features results in more accurate classifications. We introduce eigenregions, which are geometrical features that encompass area, location and shape properties of an image region, even if the region is spatially incoherent. Eigenregions are calculated using principal component analysis (PCA). On a database of 77'000 different regions obtained through the segmentation of 13'500 real-scene photographic i

This comprehensive treatise, featuring the history and historical processes of photography, contemporary applications, and the new and evolving digital technologies, will provide the most accurate technical synopsis of the current, as well as early worlds of photography ever compiled. This Encyclopedia, produced by a team of world renown practicing experts, shares in highly detailed descriptions, the core concepts and facts relative to anything photographic. This Fourth edition of the Focal Encyclopedia ser

This paper explores the use of joint colour and near-infrared (NIR) information for feature based matching and image registration. In particular, we investigate multispectral generalisations of two popular interest point detectors (Harris and difference of ...

Computer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks of existing methods, we empirically c ...

Visual cognition is of significant importance in certain imaging applications, such as security and surveillance. In these applications, an important issue is to determine the cognition threshold, which is the maximum distortion level that can be applied t ...

A computer-implemented video completion method is proposed for reconstructing a sparsely sampled video comprising sparsely sampled video frames comprising sparse sets of picture element intensity values. The method comprises: distributing the sparse sets o ...

Artists often want to change the colors of an image to achieve a particular aesthetic goal. For example, they might limit colors to a warm or cool color scheme to create an image with a certain mood or feeling. Gamut masking is a technique that artists use ...

Extreme image or video completion, where, for instance, we only retain 1% of pixels in random locations, allows for very cheap sampling in terms of the required pre-processing. The consequence is, however, a reconstruction that is challenging for humans an ...

We review the AIM 2020 challenge on virtual image relighting and illumination estimation. This paper presents the novel VIDIT dataset used in the challenge and the different proposed solutions and final evaluation results over the 3 challenge tracks. The f ...

We present a method to give color advice for Home Décor using images of room finishes, such as paint, flooring, or textiles, taken with uncalibrated cameras. Due to variations in color rendering across devices, an object imaged with different cameras will ...

Deep image denoisers achieve state-of-the-art results but with a hidden cost. As witnessed in recent literature, these deep networks are capable of overfitting their training distributions, causing inaccurate hallucinations to be added to the output and ge ...

We present an optimization technique to find hue constant RGB sensors. The hue representation is based on a log RGB opponent color space that is invariant to brightness and gamma. While modeling the visual response did not derive the opponent space, the hue definition is similar to the ones found in CIE Lab and IPT. Finding hue constant RGB sensors through this optimization might be applicable in color engineering applications such as finding RGB sensors for color image encodings.

Relightable photographs are alternatives to traditional photographs as they provide a richer viewing experience. However, the complex acquisition systems of existing techniques have restricted its usage to specialized setups. We introduce an easy-to-use an ...

Sabine Süsstrunk

Chat with Graph Search

Optimizing Latent Space Directions For GAN-based Local Image Editing

RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering

VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text

Subtractive Modulative Network with Learnable Periodic Activations

MulT: An End-to-End Multitask Learning Transformer

Super-Resolution from Highly Undersampled Images

VIDIT: Virtual Image Dataset for Illumination Transfer

Eigenregions for Image Classification

Image Formation, Colorimetry, Color Spaces, Color Encodings and Color Image Encodings, Color Management

Multispectral Interest Points for RGB-NIR Image Registration

SLIC Superpixels Compared to State-of-the-art Superpixel Methods

Analyzing Near-infrared Images for Utility Assessment

Adaptive extreme video completion

An Interactive Tool for Gamut Masking

Divergence-Based Adaptive Extreme Video Completion

AIM 2020: Scene Relighting and Illumination Estimation Challenge

A Home Décor expert in your camera

Image Denoising with Control over Deep Network Hallucination

Optimization for Hue Constant RGB Sensors

Handheld reflectance acquisition of paintings