4 papers
Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment
Ziyao Wang, Maonan Wang, Yucheng He +5
Cloud removal (CR) is essential for optical remote sensing, serving as a prerequisite for reliable downstream interpretation, such as semantic segmentation and change detection. Ho…
InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization
Hongyang Zhang, Maonan Wang, Ziyao Wang +2
Cross-view geo-localization (CVGL) is fundamental for precise localization and navigation in GPS-denied environments, aiming to match ground or UAV imagery with satellite views. Ex…
BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs
Zhantao Yang, Ruili Feng, Keyu Yan +13
Advancements in large Vision-Language Models have brought precise, accurate image captioning, vital for advancing multi-modal image understanding and processing. Yet these captions…
The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control
Ruili Feng, Han Zhang, Zhantao Yang +7
We present The Matrix, the first foundational realistic world simulator capable of generating continuous 720p high-fidelity real-scene video streams with real-time, responsive cont…