This paper aims to introduce the concept and objectives of the recently funded AI-OBSERVER Horizon Europe Twinning project titled “Enhancing Earth Observation capabilities of the Eratosthenes Centre of Excellence on Disaster Risk Reduction through Artificial Intelligence”. The AIOBSERVER project aims to significantly strengthen and stimulate the scientific excellence and innovation capacity of the ERATOSTHENES Centre of Excellence on the use of Artificial Intelligence for Earth Observation in the Disaster Risk Reduction thematic area, as well as the research management and administrative skills, of the Centre. This will be achieved through a series of capacity building and targeted research activities, having the support of internationally leading institutions, i.e., the German Research Centre for Artificial Intelligence from Germany and the University of Rome Tor Vergata from Italy, assisting the ERATOSTHENES Centre of Excellence to reach its longterm objective of raised excellence on Artificial Intelligence for Earth Observation on environmental hazards.

Abstract Moving around in a virtual world is one of the essential interactions for Virtual Reality (VR) applications. The current standard for moving in VR is using a controller. Recently, VR Head Mounted Displays integrate new input modalities such as hand tracking which allows the investigation of different techniques to move in VR. This work explores different techniques for bare-handed locomotion since it could offer a promising alternative to existing freehand techniques. The presented techniques enable continuous movement through an immersive virtual environment. The proposed techniques are compared to each other in terms of efficiency, usability, perceived workload, and user preference.

We propose RPSRNet - a novel end-to-end trainable deep neural network for rigid point set registration. For this task, we use a novel 2D-tree representation for the input point sets and a hierarchical deep feature embedding in the neural network. An iterative transformation refinement module of our network boosts the feature matching accuracy in the intermediate stages. We achieve an inference speed of ∼12-15 ms to register a pair of input point clouds as large as ∼250K. Extensive evaluations on (i) KITTI LiDAR-odometry and (ii) ModelNet-40 datasets show that our method outperforms prior state-of-the-art methods – e.g., on the KITTI dataset, DCP-v2 by 1.3 and 1.5 times, and PointNetLK by 1.8 and 1.9 times better rotational and translational accuracy respectively. Evaluation on ModelNet40 shows that RPSRNet is more robust than other benchmark methods when the samples contain a significant amount of noise and disturbance. RPSRNet accurately registers point clouds with non-uniform sampling densities, e.g., LiDAR data, which cannot be processed by many existing deep-learning-based registration methods.

Auto-Calibration is an important task in computer vision and is necessary for many visual applications. Methods like photogrammetry, depth map estimation, metrology, augmented/mixed reality or odometry are strongly dependent on well calibrated devices. While classical calibration relies on tools like checkerboards or additional scene information, auto-calibration only takes epipolar relations into account. Classical calibration is often impractical, tends to de-adjust over time and distributes the error over the entire, limited working volume. Auto-calibration, on the other hand, does not require any information other than the image content itself, has a virtually unlimited working range and usually achieves highest accuracy at the objects' surfaces. Unfortunately, auto-calibration methods are sensitive to errors in the fundamental matrix and need good initialization to converge to the global solution. In practice this leads to difficulties if optical parameters like principal point or focal length are unconstrained. In such situations, even state-of- the-art auto-calibration methods tend to diverge and do not yield a valid calibration. This work assesses reasons for this behavior, in particular for the initialization method of Bougnoux [3] and Lourakis' state-of-the-art auto-calibration method [21]. Based on the analysis, a more stable method is proposed. A continuous and smooth energy functional is introduced, providing superior convergence properties. I.e. it can not diverge, converges faster, and has a significantly enlarged convergence region with respect to the global minimum. Finally, a thorough evaluation has been conducted and a detailed comparison with the state of the art is presented.

The problem of dense point set registration, given a sparse set of prior correspondences, often arises in computer vision tasks. Unlike in the rigid case, integrating prior knowledge into a registration algorithm is especially demanding in the non-rigid case due to the high variability of motion and deformation. In this paper we present the Extended Coherent Point Drift registration algorithm. It enables, on the one hand, to couple correspondence priors into the dense registration procedure in a closed form and, on the other hand, to process large point sets in reasonable time through adopting an optimal coarse-to-fine strategy. Combined with a suitable keypoint extractor during the preprocessing step, our method allows for non-rigid registrations with increased accuracy for point sets with structured outliers. We demonstrate advantages of our approach against other non-rigid point set registration methods in synthetic and real-world scenarios.

We present OrcaM, a device for exploring new methods in the field of simultaneous acquisition of geometry, color and reflectance properties. OrcaM employs a full-spherical construction, a movable projector-camera unit, 633 individually controllable LEDs and a height-adjustable turntable with a glass carrier. In contrast to state of the art hardware layouts, this design allows data acquisition from all possible directions in a single pass without any user interaction. In this paper we report the challenges we encountered during development. We describe the used calibration algorithms that constitute the basis for all future reconstruction methods and present results computed with the methods we currently use.

We present a novel GPU-based algorithm for high-quality rendering of bivariate spline surfaces. An essential difference to the known methods for rendering graph surfaces is that we use quartic smooth splines on triangulations rather than triangular meshes. Our rendering approach is direct in the sense that since we do not use an intermediate tessellation but rather compute ray-surface intersections (by solving quartic equations numerically) as well as surface normals (by using Bernstein-Bézier techniques) for Phong illumination on the GPU. Inaccurate shading and artifacts appearing for triangular tesselated surfaces are completely avoided. Level of detail is automatic since all computations are done on a per fragment basis. We compare three different (quasi-) interpolating schemes for uniformly sampled gridded data, which differ in the smoothness and the approximation properties of the splines. The results show that our hardware based renderer leads to visualizations (including texturing, multiple light sources, environment mapping, etc.) of highest quality.

We present a new algorithm extracting and fairing surfaces from segmented volumes composed of multiple materials. In a first pass, the material boundaries in the volume are smoothed considering signed distance functions for the individual materials. Second, we apply a marching-cubes-like contouring method providing initial meshes defining material boundaries. Non-manifold features emerge along lines where more than two materials encounter. Finally, the mesh geometry is relaxed in a constrained fairing process. We use our algorithm to construct a heart model from segmented time-varying magnetic resonance images. Information concerning the heart ontology is used to merge certain structures to functional units.