4 papers
A Controlled Evaluation of Model Rankings and Input Reliance in Surface Water Segmentation
Kittipat Phunjanna, Kristóf Karacs, Chayut Ngamkhanong
Performance evaluation for surface-water segmentation commonly uses an aggregate metric such as global intersection-over-union (IoU) to rank model configurations. However, a config…
SceneVGGT: VGGT-based online 3D semantic SLAM for indoor scene understanding and navigation
Anna Gelencsér-Horváth, Gergely Dinya, Dorka Boglárka Erős +3
We present SceneVGGT, a spatio-temporal 3D scene understanding framework that combines SLAM with semantic mapping for autonomous and assistive navigation. Built on VGGT, our method…
SAMannot: A Memory-Efficient, Local, Open-source Framework for Interactive Video Instance Segmentation based on SAM2
Gergely Dinya, András Gelencsér, Krisztina Kupán +3
Current research workflows for precise video segmentation are often forced into a compromise between labor-intensive manual curation, costly commercial platforms, and/or privacy-co…
Building temporally coherent 3D maps with VGGT for memory-efficient Semantic SLAM
Gergely Dinya, Péter Halász, András Lőrincz +2
We present a fast, spatio-temporal scene understanding framework based on Visual Geometry Grounded Transformer (VGGT). The proposed pipeline is designed to enable efficient, close…