Related papers: How to Train a CAT: Learning Canonical Appearance …

We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the…

We present a deep learning-based method for propagating spatially-varying visual material attributes (e.g. texture maps or image stylizations) to larger samples of the same or similar materials. For training, we leverage images of the…

Many tasks in computer vision can be cast as a "label changing" problem, where the goal is to make a semantic change to the appearance of an image or some subject in an image in order to alter the class membership. Although successful…

Accurate camera localization is an essential part of tracking systems. However, localization results are greatly affected by illumination. Including data collected under various lighting conditions can improve the robustness of the…

Canonicalization is a widely used strategy in equivariant machine learning, enforcing symmetry in neural networks by mapping each input to a standard form. Yet, it often introduces discontinuities that can affect stability during training,…

Visual error metrics play a fundamental role in the quantification of perceived image similarity. Most recently, use cases for them in real-time applications have emerged, such as content-adaptive shading and shading reuse to increase…

Learning-based image harmonization techniques are usually trained to undo synthetic random global transformations applied to a masked foreground in a single ground truth photo. This simulated data does not model many of the important…

Visual prompting infuses visual information into the input image to adapt models toward specific predictions and tasks. Recently, manually crafted markers such as red circles are shown to guide the model to attend to a target region on the…

Pansharpening is a crucial remote sensing technique that fuses low-resolution multispectral (LRMS) images with high-resolution panchromatic (PAN) images to generate high-resolution multispectral (HRMS) imagery. Although deep learning…

Employing machine learning models in the real world requires collecting large amounts of data, which is both time consuming and costly to collect. A common approach to circumvent this is to leverage existing, similar data-sets with large…

Recognising relevant objects or object states in its environment is a basic capability for an autonomous robot. The dominant approach to object recognition in images and range images is classification by supervised machine learning,…

Visual localization techniques often comprise a hierarchical localization pipeline, with a visual place recognition module used as a coarse localizer to initialize a pose refinement stage. While improving the pose refinement step has been…

Localization in topological maps is essential for image-based navigation using an RGB camera. Localization using only one camera can be challenging in medium-to-large-sized environments because similar-looking images are often observed…

This work proposes a process for efficiently training a point-wise object detector that enables localizing objects and computing their 6D poses in cluttered and occluded scenes. Accurate pose estimation is typically a requirement for robust…

Topological localization is a fundamental problem in mobile robotics, since robots must be able to determine their position in order to accomplish tasks. Visual localization and place recognition are challenging due to perceptual ambiguity,…

Deep networks have become very popular over the past few years. The main reason for this widespread use is their excellent ability to learn and predict knowledge in a very easy and efficient way. Convolutional neural networks and…

We propose a self-supervised training approach for learning view-invariant dense visual descriptors using image augmentations. Unlike existing works, which often require complex datasets, such as registered RGBD sequences, we train on an…

Scene classification is a fundamental perception task for environmental understanding in today's robotics. In this paper, we have attempted to exploit the use of popular machine learning technique of deep learning to enhance scene…

We tackle the problem of visual localization under changing conditions, such as time of day, weather, and seasons. Recent learned local features based on deep neural networks have shown superior performance over classical hand-crafted local…

Training a deep network to perform semantic segmentation requires large amounts of labeled data. To alleviate the manual effort of annotating real images, researchers have investigated the use of synthetic data, which can be labeled…