3 papers
cs.CV2026
Venice-H1: Failure-Aware Query Re-Ranking with Multi-Scale Grid Signatures for Referring Image Segmentation
Nicolò Savioli
Modern Referring Image Segmentation (RIS) systems generate multiple candidate masks per expression but rely on a simple heuristic--typically the argmax detection score--to select t…
cs.CV2025
Lane Graph Extraction from Aerial Imagery via Lane Segmentation Refinement with Diffusion Models
Antonio Ruiz, Andrew Melnik, Nicolo Savioli +3
The lane graph is critical for applications such as autonomous driving and lane-level route planning. While previous research has focused on extracting lane-level graphs from aeria…
cs.CV2025
Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text
Xuyang Chen, Dong Wang, Konrad Schindler +4
Recently, Transformer-based text detection techniques have sought to predict polygons by encoding the coordinates of individual boundary vertices using distinct query features. How…