Related papers: Maximizing Self-supervision from Thermal Image for…

Depth estimation is critical for any robotic system. In the past years estimation of depth from monocular images have shown great improvement, however, in the underwater environment results are still lagging behind due to appearance changes…

The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such…

Thermal images are mainly used to detect the presence of people at night or in bad lighting conditions, but perform poorly at daytime. To solve this problem, most state-of-the-art techniques employ a fusion network that uses features from…

Capturing images under extremely low-light conditions poses significant challenges for the standard camera pipeline. Images become too dark and too noisy, which makes traditional enhancement techniques almost impossible to apply. Recently,…

Learning to predict scene depth from RGB inputs is a challenging task both for indoor and outdoor robot navigation. In this work we address unsupervised learning of scene depth and robot ego-motion where supervision is provided by monocular…

Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos,…

Methods for generating synthetic data have become of increasing importance to build large datasets required for Convolution Neural Networks (CNN) based deep learning techniques for a wide range of computer vision applications. In this work,…

The ability to accurately estimate depth information is crucial for many autonomous applications to recognize the surrounded environment and predict the depth of important objects. One of the most recently used techniques is monocular depth…

Under difficult environmental conditions, the view of RGB cameras may be restricted by fog, dust or difficult lighting situations. Because thermal cameras visualize thermal radiation, they are not subject to the same limitations as RGB…

Self-supervised learning has made unsupervised pretraining relevant again for difficult computer vision tasks. The most effective self-supervised methods involve prediction tasks based on features extracted from diverse views of the data.…

Designing egocentric 3D hand pose estimation systems that can perform reliably in complex, real-world scenarios is crucial for downstream applications. Previous approaches using RGB or NIR imagery struggle in challenging conditions: RGB…

Inferring past human motion from RGB images is challenging due to the inherent uncertainty of the prediction problem. Thermal images, on the other hand, encode traces of past human-object interactions left in the environment via thermal…

Depth-guided multimodal fusion combines depth information from visible and infrared images, significantly enhancing the performance of 3D reconstruction and robotics applications. Existing thermal-visible image fusion mainly focuses on…

6D pose estimation pipelines that rely on RGB-only or RGB-D data show limitations for photometrically challenging objects with e.g. textureless surfaces, reflections or transparency. A supervised learning-based method utilising…

Image denoising is of great importance for medical imaging system, since it can improve image quality for disease diagnosis and downstream image analyses. In a variety of applications, dynamic imaging techniques are utilized to capture the…

Accurate feature matching and correspondence in endoscopic images play a crucial role in various clinical applications, including patient follow-up and rapid anomaly localization through panoramic image generation. However, developing…

Photometric loss is widely used for self-supervised depth and egomotion estimation. However, the loss landscapes induced by photometric differences are often problematic for optimization, caused by plateau landscapes for pixels in…

Depth information is important for autonomous systems to perceive environments and estimate their own state. Traditional depth estimation methods, like structure from motion and stereo vision matching, are built on feature correspondences…

Merging multi-exposure images is a common approach for obtaining high dynamic range (HDR) images, with the primary challenge being the avoidance of ghosting artifacts in dynamic scenes. Recent methods have proposed using deep neural…

Visual place recognition (VPR) using deep networks has achieved state-of-the-art performance. However, most of them require a training set with ground truth sensor poses to obtain positive and negative samples of each observation's spatial…