Related papers: Leveraging Color Channel Independence for Improved…
Hyperspectral images super-resolution aims to improve the spatial resolution, yet its performance is often limited at high-resolution ratios. The recent adoption of high-resolution reference images for super-resolution is driven by the poor…
Unsupervised object-centric representation (OCR) learning has recently drawn attention as a new paradigm of visual representation. This is because of its potential of being an effective pre-training technique for various downstream tasks in…
Cross-spectral biometrics, such as matching imagery of faces or persons from visible (RGB) and infrared (IR) bands, have rapidly advanced over the last decade due to increasing sensitivity, size, quality, and ubiquity of IR focal plane…
Vector quantised variational autoencoders (VQ-VAE) are characterised by three main components: 1) encoding visual data, 2) assigning $k$ different vectors in the so-called embedding space, and 3) decoding the learnt features. While images…
Object-centric understanding is fundamental to human vision and required for complex reasoning. Traditional methods define slot-based bottlenecks to learn object properties explicitly, while recent self-supervised vision models like DINO…
Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can…
Image colorization is the process of colorizing grayscale images or recoloring an already-color image. This image manipulation can be used for grayscale satellite, medical and historical images making them more expressive. With the help of…
In this thesis we discuss architectural designs and training methods for a neural network to have the ability of dissecting an image into objects of interest without supervision. The main challenge in 2D unsupervised object segmentation is…
Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built. Recent work on simple 2D and 3D datasets has shown that models…
Research in child development has shown that embodied experience handling physical objects contributes to many cognitive abilities, including visual learning. One characteristic of such experience is that the learner sees the same object…
Most of computer vision focuses on what is in an image. We propose to train a standalone object-centric context representation to perform the opposite task: seeing what is not there. Given an image, our context model can predict where…
Edge-based computer vision models running on compact, resource-limited devices benefit greatly from using unprocessed, detail-rich RAW sensor data instead of processed RGB images. Training these models, however, necessitates large labeled…
In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination. Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most…
Color vision is essential for human visual perception, but its impact on machine perception is still underexplored. There has been an intensified demand for understanding its role in machine perception for safety-critical tasks such as…
Segmenting unseen objects in cluttered scenes is an important skill that robots need to acquire in order to perform tasks in new environments. In this work, we propose a new method for unseen object instance segmentation by learning RGB-D…
Several machine learning tasks require to represent the data using only a sparse set of interest points. An ideal detector is able to find the corresponding interest points even if the data undergo a transformation typical for a given…
Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While…
Estimating depth from a single RGB images is a fundamental task in computer vision, which is most directly solved using supervised deep learning. In the field of unsupervised learning of depth from a single RGB image, depth is not given…
Hyperspectral imaging empowers machine vision systems with the distinct capability of identifying materials through recording their spectral signatures. Recent efforts in data-driven spectral reconstruction aim at extracting spectral…
The vast majority of standard image and video content available online is represented in display-encoded color spaces, in which pixel values are conveniently scaled to a limited range (0-1) and the color distribution is approximately…