arXiv AI
Component-Aware Structure-Preserving Style Transfer for Satellite Visual Sim2Real Data Construction
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 24
SatUnreal: A High-Precision Synthetic Dataset for Satellite Stereo Matching via Unreal Engine
SatUnreal is a synthetic dataset created with Unreal Engine that offers 10,000 high‑resolution (0.3 m GSD) satellite stereo pairs. It addresses key limitations of existing benchmarks by ensuring physical geometry simulation, spatio‑temporal consistency, topographic diversity, and mathematically precise occlusion masks via a two‑step line‑trace algorithm. Models trained solely on SatUnreal outperform those trained on real datasets when transferred to real‑world benchmarks such as US3D and WHU‑Stereo.
arXiv Computer Vision
Oct 1
Curating Synthetic Data for Task-Specific Visual Perception
arXiv:2609.38476v1 Announce Type: new Abstract: Synthetic data are most valuable where general-purpose datasets cannot provide the domain-specific priors a task requires, and where manual annotation...
arXiv Computer Vision
Aug 21
YOLOv14: Adaptive Real-Time Object Detection for Diverse Imaging Conditions
arXiv:2608. 04720v4 Announce Type: replace Abstract: Real-time object detectors achieve remarkable accuracy under controlled conditions, yet degrade sharply on non-ideal inputs-fisheye distortion, game-rendered content, aerial views, and 360{\deg}panoramas.
arXiv Computer Vision
Sep 10
Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image
arXiv:2606.24138v2 Announce Type: replace Abstract: Generating explicit textured 3D city assets from a single satellite image is important for urban simulation and digital twins. Most prior methods,...
arXiv Machine Learning
Jun 25
Benchmarking the Alignment of Data-Quality Metrics, Human Judgment and Land-Cover Segmentation Performance for Earth Observation
arXiv:2606. 25128v1 Announce Type: cross Abstract: Volume and quality of datasets are crucial for deep learning model training, yet they are often constrained by availability and data acquisition costs.
arXiv Computer Vision
Oct 7
RenderBench: Benchmarking Render-to-Real Video Transfer with Reconstructed Digital Twins
arXiv:2610.08684v1 Announce Type: new Abstract: Modern video models can generate realistic videos from real appearance references and proxy renders that specify scene structure, viewpoint changes, an...