Related papers: GENESIS: Co-location of Geodetic Techniques in Spa…
Rotation invariance is an important requirement for point shape analysis. To achieve this, current state-of-the-art methods attempt to construct the local rotation-invariant representation through learning or defining the local reference…
Urban environments are continuously mapped and modeled by various data collection platforms, including satellites, unmanned aerial vehicles and street cameras. The growing availability of 3D geospatial data from multiple modalities has…
A rigorous approach to simultaneously determine a Terrestrial Reference Frame (TRF) and Earth Orientation Parameters (EOP) is now currently applied on a routine basis in a coordinated project within the Groupe de Recherches de G\'eod\'esie…
Neural Radiance Fields (NeRF) offer the potential to benefit 3D reconstruction tasks, including aerial photogrammetry. However, the scalability and accuracy of the inferred geometry are not well-documented for large-scale aerial…
Accurate and continuous monitoring of Earth's gravity field is essential for tracking mass redistribution processes linked to climate variability, hydrological cycles, and geodynamic phenomena. While the GRACE and GRACE Follow-On (GRACE-FO)…
Recent advances in Neural Radiance Fields (NeRF) have demonstrated promising results in 3D scene representations, including 3D human representations. However, these representations often lack crucial information on the underlying human pose…
3D Gaussian Splatting (3DGS) has emerged as a leading technique for novel view synthesis, demonstrating exceptional rendering efficiency. \replaced[]{Well-reconstructed surfaces can be characterized by low configurational entropy, where…
The drone navigation requires the comprehensive understanding of both visual and geometric information in the 3D world. In this paper, we present a Visual-Geometric Fusion Network(VGF-Net), a deep network for the fusion analysis of…
In this thesis, we leverage monocular cameras on aerial robots to predict depth and semantic maps in low-altitude unstructured environments. We propose a joint deep-learning architecture, named Co-SemDepth, that can perform the two tasks…
Text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models has shown great promise but still suffers from inconsistent 3D geometric structures (Janus problems) and severe artifacts. The aforementioned problems…
We introduce Geo-NVS-w, a geometry-aware framework for high-fidelity novel view synthesis from unstructured, in-the-wild image collections. While existing in-the-wild methods already excel at novel view synthesis, they often lack geometric…
Generalized visual grounding tasks, including Generalized Referring Expression Comprehension (GREC) and Segmentation (GRES), extend the classical visual grounding paradigm by accommodating multi-target and non-target scenarios.…
The changes in phase, time and frequency suffered by signals when retransmitted by a remote and inaccessible transponder and the propagation delays are major constraints to obtain accurate ranging measurements in various related…
To overcome the innovation gap of the Guidance, Navigation and Control (GNC) design process between research and industrial practice a benchmark of industrial relevance has been developed and is presented. This initiative is driven as well…
Hydrogeodesy can benefit greatly from the use of Global Positioning System (GPS) displacements to analyse local changes in the hydrosphere, which the commonly used Gravity Recovery and Climate Experiment (GRACE) mission is unable to provide…
The ability to accurately evaluate the performance of location determination systems is crucial for many applications. Typically, the performance of such systems is obtained by comparing ground truth locations with estimated locations.…
In many applications, maintaining a consistent map of the environment is key to enabling robotic platforms to perform higher-level decision making. Detection of already visited locations is one of the primary ways in which map consistency…
Neural radiance fields~(NeRF) have recently been applied to render large-scale scenes. However, their limited model capacity typically results in blurred rendering results. Existing large-scale NeRFs primarily address this limitation by…
Geometric estimation is required for scene understanding and analysis in panoramic 360{\deg} images. Current methods usually predict a single feature, such as depth or surface normal. These methods can lack robustness, especially when…
Thermochemistry, ray-tracing radiation, and radiation-matter interactions are important processes which are computationally difficult to model in astrophysical simulations, addressed by introducing novel algorithms optimized for…