Abstract: Video object segmentation (VOS) requires robust tracking and segmentation of objects over long video sequences. Existing methods often suffer from error ...

Abstract: Segment Anything Model 2 (SAM2) has demonstrated state-of-the-art performance in image/video object segmentation across many domains, but its large encoder makes it challenging for ...

OBER (OBject-Effect Removal) is a hybrid dataset designed to support research in object removal with effects, combining both camera-captured and simulated data. 🔥 We have released the full dataset ...

Data used for Wheat3DGS and the baseline results for each plot (from 461 to 467) are structured as follows: Note that resolution is set to 1 to prevent image downscaling, and the training/test split ...