Related papers: DiffusionUavLoc: Visually Prompted Diffusion for C…
Cross-view geolocalization, a supplement or replacement for GPS, localizes an agent within a search area by matching ground-view images to overhead images. Significant progress has been made assuming a panoramic ground camera. Panoramic…
Diffusion probabilistic models have been shown to generate state-of-the-art results on several competitive image synthesis benchmarks but lack a low-dimensional, interpretable latent space, and are slow at generation. On the other hand,…
Safe swarm navigation in cluttered indoor environment requires long-horizon planning, reactive obstacle avoidance, and adaptive compliance. We propose ImpedanceDiffusion, a hierarchical framework that leverages image-conditioned…
A novel prize-winner algorithm designed for a path following problem within the Unmanned Aerial Vehicle (UAV) field is presented in this paper. The proposed approach exploits the advantages offered by the pure pursuing algorithm to set up…
Unmanned aerial vehicles (UAVs) visual localization in planetary aims to estimate the absolute pose of the UAV in the world coordinate system through satellite maps and images captured by on-board cameras. However, since planetary scenes…
Underwater vision is crucial for autonomous underwater vehicles (AUVs), and enhancing degraded underwater images in real-time on a resource-constrained AUV is a key challenge due to factors like light absorption and scattering, or the…
With the expanding application scope of unmanned aerial vehicles (UAVs), the demand for stable UAV control has significantly increased. However, in complex environments, GPS signals are prone to interference, resulting in ineffective UAV…
Accurate pose estimation is fundamental for unmanned aerial vehicle (UAV) applications, where Visual-Inertial SLAM (VI-SLAM) provides a cost-effective solution for localization and mapping. However, existing VI-SLAM methods mainly rely on…
Geospatial imaging leverages data from diverse sensing modalities-such as EO, SAR, and LiDAR, ranging from ground-level drones to satellite views. These heterogeneous inputs offer significant opportunities for scene understanding but…
We propose Context Diffusion, a diffusion-based framework that enables image generation models to learn from visual examples presented in context. Recent work tackles such in-context learning for image generation, where a query image is…
The localization of Unmanned aerial vehicles (UAVs) in deep tunnels is extremely challenging due to their inaccessibility and hazardous environment. Conventional outdoor localization techniques (such as using GPS) and indoor localization…
The performance of leaning-based perception algorithms suffer when deployed in out-of-distribution and underrepresented environments. Outdoor robots are particularly susceptible to rapid changes in visual scene appearance due to dynamic…
Diffusion-based robot navigation policies trained on large-scale imitation learning datasets, can generate multi-modal trajectories directly from the robot's visual observations, bypassing the traditional localization-mapping-planning…
The scarcity and complexity of voxel-level annotations in 3D medical imaging present significant challenges, particularly due to the domain gap between labeled datasets from well-resourced centers and unlabeled datasets from less-resourced…
Recent advancements in text-to-image diffusion models have demonstrated remarkable success, yet they often struggle to fully capture the user's intent. Existing approaches using textual inputs combined with bounding boxes or region masks…
This paper introduces innovative solutions to enhance spatial controllability in diffusion models reliant on text queries. We first introduce vision guidance as a foundational spatial cue within the perturbed distribution. This…
Accurate indoor positioning for unmanned aerial vehicles (UAVs) is critical for logistics, surveillance, and emergency response applications, particularly in GPS-denied environments. Existing indoor localization methods, including optical…
Text-guided domain adaptation and generation of 3D-aware portraits find many applications in various fields. However, due to the lack of training data and the challenges in handling the high variety of geometry and appearance, the existing…
The use of unmanned aerial vehicles (UAVs) is strongly advocated for sixth-generation (6G) networks, as the 6G standard will not be limited to improving broadband services, but will also target the extension of the geographical cellular…
Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this…