Related papers: Blind Augmentation: Calibration-free Camera Distor…
Camera calibration for estimating the intrinsic parameters and lens distortion is a prerequisite for various monocular vision applications including feature tracking and video stabilization. This application paper proposes a model for…
Deep learning approaches have become the standard solution to many problems in computer vision and robotics, but obtaining sufficient training data in high enough quality is challenging, as human labor is error prone, time consuming, and…
Nearly all 3D displays need calibration for correct rendering. More often than not, the optical elements in a 3D display are misaligned from the designed parameter setting. As a result, 3D magic does not perform well as intended. The…
Although Neural Radiance Fields (NeRFs) have markedly improved novel view synthesis, accurate uncertainty quantification in their image predictions remains an open problem. The prevailing methods for estimating uncertainty, including the…
For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in…
Image and video quality in Long Range Observation Systems (LOROS) suffer from atmospheric turbulence that causes small neighbourhoods in image frames to chaotically move in different directions and substantially hampers visual analysis of…
In this paper, we discuss an imitation learning based method for reducing the calibration error for a mixed reality system consisting of a vision sensor and a projector. Unlike a head mounted display, in this setup, augmented information is…
Wide field-of-view (FOV) cameras, which capture a larger scene area than narrow FOV cameras, are used in many applications including 3D reconstruction, autonomous driving, and video surveillance. However, wide-angle images contain…
Diverse data augmentation strategies are a natural approach to improving robustness in computer vision models against unforeseen shifts in data distribution. However, the ability to tailor such strategies to inoculate a model against…
Image denoising has achieved unprecedented progress as great efforts have been made to exploit effective deep denoisers. To improve the denoising performance in realworld, two typical solutions are used in recent trends: devising better…
Recently, it is increasingly popular to equip mobile RGB cameras with Time-of-Flight (ToF) sensors for active depth sensing. However, for off-the-shelf ToF sensors, one must tackle two problems in order to obtain high-quality depth with…
Consistency training regularizes a model by enforcing predictions of original and perturbed inputs to be similar. Previous studies have proposed various augmentation methods for the perturbation but are limited in that they are agnostic to…
Data augmentation has recently emerged as an essential component of modern training recipes for visual recognition tasks. However, data augmentation for video recognition has been rarely explored despite its effectiveness. Few existing…
Spatial scene-understanding, including dense depth and ego-motion estimation, is an important problem in computer vision for autonomous vehicles and advanced driver assistance systems. Thus, it is beneficial to design perception modules…
Fast binary descriptors build the core for many vision based applications with real-time demands like object detection, Visual Odometry or SLAM. Commonly it is assumed, that the acquired images and thus the patches extracted around…
Camera calibration involves estimating camera parameters to infer geometric features from captured sequences, which is crucial for computer vision and robotics. However, conventional calibration is laborious and requires dedicated…
This paper demonstrates a practical method that can correct spatial varying blur from a set of images of the same object. The algorithm jointly estimates the object and local point spread functions~(PSF). The method prioritizes sections…
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically show data augmentation might introduce noisy augmented examples and consequently hurt the performance on…
Autonomous vehicles and robots require increasingly more robustness and reliability to meet the demands of modern tasks. These requirements specially apply to cameras onboard such vehicles because they are the predominant sensors to acquire…
X-ray imaging is a fundamental tool of routine clinical diagnosis. Fluoroscopic imaging can further acquire X-ray images at video frame rates, thus enabling non-invasive in-vivo motion studies of joints, gastrointestinal tract, etc. For…