Related papers: Multi-modal, multi-scale representation learning f…

Scale arbitrary super-resolution based on implicit image function gains increasing popularity since it can better represent the visual world in a continuous manner. However, existing scale arbitrary works are trained and evaluated on…

Image super-resolution (SR) has significantly advanced through the adoption of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention window to capture broader contexts come with inherent…

The rapid expansion of multi-source satellite imagery drives innovation in Earth observation, opening unprecedented opportunities for Remote Sensing Foundation Models to harness diverse data. However, many existing models remain constrained…

Heterodyne receivers register the sky signal on either a circular polarization basis (where it is split into left-hand and right-hand circular polarization) or a linear polarization basis (where it is split into horizontal and vertical…

There is an increasing number of real-world problems in computer vision and machine learning requiring to take into consideration multiple interpretation layers (modalities or views) of the world and learn how they relate to each other. For…

Earth observation with small satellites serves a wide range of relevant applications. However, significant advances in sensor technology (e.g., higher resolution, multiple spectrums beyond visible light) in combination with challenging…

Publicly available satellite imagery can be an ubiquitous, cheap, and powerful tool for vehicle localisation when a prior sensor map is unavailable. However, satellite images are not directly comparable to data from ground range sensors…

We propose the Lightweight Multimodal Contrastive Attention Transformer (L-MCAT), a novel transformer-based framework for label-efficient remote sensing image classification using unpaired multimodal satellite data. L-MCAT introduces two…

In this work, we propose an extension of conventional image data by an additional channel in which the associated projection properties are encoded. This addresses the issue of sensor-dependent object representation in projection-based…

In this paper, we develop a novel super-resolution algorithm for near-field synthetic-aperture radar (SAR) under irregular scanning geometries. As fifth-generation (5G) millimeter-wave (mmWave) devices are becoming increasingly affordable…

Intrinsic image decomposition aims at separating an image into its underlying albedo and shading components, isolating the base color from lighting effects to enable downstream applications such as virtual relighting and scene editing.…

Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning. Due to the high variability inherent in satellite data, most of the current object classification…

By sending one or more telescopes into space, Space-VLBI (SVLBI) is able to achieve even higher angular resolution and is therefore the trend of the VLBI technique. For SVLBI program, the design of satellite orbits plays an important role…

Current few-shot learning models capture visual object relations in the so-called meta-learning setting under a fixed-resolution input. However, such models have a limited generalization ability under the scale and location mismatch between…

The feature based spatial verification method SAL is applied to cloud data, i.e. two-dimensional spatial fields of total cloud cover and spectral radiance. Model output is obtained from the COSMO-DE forward operator SynSat and compared to…

Accurate hyperspectral image (HSI) interpretation is critical for providing valuable insights into various earth observation-related applications such as urban planning, precision agriculture, and environmental monitoring. However, existing…

Whole-slide MIL models are often called context-aware once graphs, Transform ers, or state-space modules are placed above patch embeddings. We show that this label can be deceptive. On pathology tasks where tissue architecture is part of…

This thesis introduces "Embodied Spatial Intelligence" to address the challenge of creating robots that can perceive and act in the real world based on natural language instructions. To bridge the gap between Large Language Models (LLMs)…

Large AI models have been widely adopted in wireless communications for channel modeling, beamforming, and resource optimization. However, most existing efforts remain limited to single-modality inputs and channel-specific objec- tives,…

For Very Long Baseline Interferometry (VLBI), the fringe spacing is extremely narrow compared to the field of view imposed by the primary beam of each element. This means that an extremely large number of resolution units can potentially be…