Quantifying the synthetic and real domain gap in aerial scene understanding
Quantifying the gap between synthetic and real-world imagery is essential for improving both transformer-based models - that rely on large volumes of data - and datasets, especially in underexplored domains like aerial scene understanding where the potential impact is significant. This paper introduces a novel methodology for scene complexity assessment using Multi-Model Consensus Metric (MMCM) and depth-based structural metrics, enabling a robust evaluation of perceptual and structural disparities between domains. Our experimental analysis, utilizing real-world (Dronescapes) and synthetic (Skyscenes) datasets, demonstrates that real-world scenes generally exhibit higher consensus among state-of-the-art vision transformers, while synthetic scenes show greater variability and challenge model adaptability. The results underline the inherent complexities and domain gaps, emphasizing the need for enhanced simulation fidelity and model generalization. This work provides critical insights into the interplay between domain characteristics and model performance, offering a pathway for improved domain adaptation strategies in aerial scene understanding.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationScene UnderstandingSimilar Papers 제목 키워드 기반
Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models
Recent advances in large-scale image generative models enable photorealistic scene synthesis with controllable attributes. Beyond data augmentation, their potential as diagnostic tools for trained vision systems remains …
Data AugmentationSkyScenes: A Synthetic Dataset for Aerial Scene Understanding
Real-world aerial scene understanding is limited by a lack of datasets that contain densely annotated images curated under a diverse set of conditions. Due to inherent challenges in obtaining such images in controlled re…
DiversityScene UnderstandingHorizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes
Seamless integration of both aerial and street view images remains a significant challenge in neural scene reconstruction and rendering. Existing methods predominantly focus on single domain, limiting their applications …
AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World
This paper addresses the problem of monocular metric depth estimation in aerial UAV imagery. Although recent data-driven methods have achieved remarkable progress in ground-level scenarios, models trained primarily on st…
Depth EstimationAerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
We explore the task of geometric reconstruction of images captured from a mixture of ground and aerial views. Current state-of-the-art learning-based approaches fail to handle the extreme viewpoint variation between aeri…
Novel View Synthesis