DSR: Towards Drone Image Super-Resolution
Despite achieving remarkable progress in recent years, single-image super-resolution methods are developed with several limitations. Specifically, they are trained on fixed content domains with certain degradations (whether synthetic or real). The priors they learn are prone to overfitting the training configuration. Therefore, the generalization to novel domains such as drone top view data, and across altitudes, is currently unknown. Nonetheless, pairing drones with proper image super-resolution is of great value. It would enable drones to fly higher covering larger fields of view, while maintaining a high image quality. To answer these questions and pave the way towards drone image super-resolution, we explore this application with particular focus on the single-image case. We propose a novel drone image dataset, with scenes captured at low and high resolutions, and across a span of altitudes. Our results show that off-the-shelf state-of-the-art networks witness a significant drop in performance on this different domain. We additionally show that simple fine-tuning, and incorporating altitude awareness into the network's architecture, both improve the reconstruction performance.
Code (1)
Tasks
Image Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
Towards Robust Drone Vision in the Wild
The past few years have witnessed the burst of drone-based applications where computer vision plays an essential role. However, most public drone-based vision datasets focus on detection and tracking. On the other hand, …
Image Super-ResolutionOne-Shot LearningSuper-ResolutionUnsupervised domain adaptation and super resolution on drone images for autonomous dry herbage biomass estimation
Herbage mass yield and composition estimation is an important tool for dairy farmers to ensure an adequate supply of high quality herbage for grazing and subsequently milk production. By accurately estimating herbage mas…
Deep LearningDomain AdaptationSuper-ResolutionUnsupervised Domain AdaptationDroneSR: Rethinking Few-shot Thermal Image Super-Resolution from Drone-based Perspective
Although large scale models achieve significant improvements in performance, the overfitting challenge still frequently undermines their generalization ability. In super resolution tasks on images, diffusion models as re…
Representation LearningImage Super-ResolutionImage ReconstructionEnhancing people localisation in drone imagery for better crowd management by utilising every pixel in high-resolution images
Accurate people localisation using drones is crucial for effective crowd management, not only during massive events and public gatherings but also for monitoring daily urban crowd flow. Traditional methods for tiny objec…
Crowd CountingManagementObjectLRDDv3: High-Resolution Long-Range Drone Detection Dataset with Range Information and Thermal Data
Unmanned Aerial Vehicles (UAVs) have quickly become common in various airspaces, representing a wide range of applications from recreation flying to commercial photography and package delivery. With the increasing preval…