Related papers: Learning to Adapt to Position Bias in Vision Trans…

For several emerging technologies such as augmented reality, autonomous driving and robotics, visual localization is a critical component. Directly regressing camera pose/3D scene coordinates from the input image using deep neural networks…

Estimating rigid objects' poses is one of the fundamental problems in computer vision, with a range of applications across automation and augmented reality. Most existing approaches adopt one network per object class strategy, depend…

The goal of a classification model is to assign the correct labels to data. In most cases, this data is not fully described by the given set of labels. Often a rich set of meaningful concepts exist in the domain that can much more precisely…

We propose a method for knowledge transfer between semantically related classes in ImageNet. By transferring knowledge from the images that have bounding-box annotations to the others, our method is capable of automatically populating…

Camera pose estimation in large-scale environments is still an open question and, despite recent promising results, it may still fail in some situations. The research so far has focused on improving subcomponents of estimation pipelines, to…

High-precision localization is pivotal in underwater reinspection missions. Traditional localization methods like inertial navigation systems, Doppler velocity loggers, and acoustic positioning face significant challenges and are not…

Attentional mechanisms are order-invariant. Positional encoding is a crucial component to allow attention-based deep model architectures such as Transformer to address sequences or images where the position of information matters. In this…

Transformation invariances are present in many real-world problems. For example, image classification is usually invariant to rotation and color transformation: a rotated car in a different color is still identified as a car. Data…

We address the problem of robot guided assembly tasks, by using a learning-based approach to identify contact model parameters for known and novel parts. First, a Variational Autoencoder (VAE) is used to extract geometric features of…

Place recognition is a critical component in robot navigation that enables it to re-establish previously visited locations, and simultaneously use this information to correct the drift incurred in its dead-reckoned estimate. In this work,…

State estimation from measured data is crucial for robotic applications as autonomous systems rely on sensors to capture the motion and localize in the 3D world. Among sensors that are designed for measuring a robot's pose, or for soft…

Image-based object pose estimation sounds amazing because in real applications the shape of object is oftentimes not available or not easy to take like photos. Although it is an advantage to some extent, un-explored shape information in 3D…

We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task…

Image classification is an essential part of computer vision which assigns a given input image to a specific category based on the similarity evaluation within given criteria. While promising classifiers can be obtained through deep…

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…

Many tasks performed by autonomous vehicles such as road marking detection, object tracking, and path planning are simpler in bird's-eye view. Hence, Inverse Perspective Mapping (IPM) is often applied to remove the perspective effect from a…

Visual localization is one of the most important components for robotics and autonomous driving. Recently, inspiring results have been shown with CNN-based methods which provide a direct formulation to end-to-end regress 6-DoF absolute…

Motivated by the need to improve model performance in traffic monitoring tasks with limited labeled samples, we propose a straightforward augmentation technique tailored for object detection datasets, specifically designed for stationary…

Image composition plays an important role in the quality of a photo. However, not every camera user possesses the knowledge and expertise required for capturing well-composed photos. While post-capture cropping can improve the composition…