5 papers
PRISM-Loc: a Lightweight Long-range LiDAR Localization in Urban Environments with Topological Maps
Kirill Muravyev, Artem Kobozev, Vasily Yuryev +4
We propose PRISM-Loc - a lightweight and robust approach for localization in large outdoor environments that combines a compact topological representation with a novel scan-matchin…
MapFM: Foundation Model-Driven HD Mapping with Multi-Task Contextual Learning
Leonid Ivanov, Vasily Yuryev, Dmitry Yudin
In autonomous driving, high-definition (HD) maps and semantic maps in bird's-eye view (BEV) are essential for accurate localization, planning, and decision-making. This paper intro…
Talk2SAM: Text-Guided Semantic Enhancement for Complex-Shaped Object Segmentation
Luka Vetoshkin, Dmitry Yudin
Segmenting objects with complex shapes, such as wires, bicycles, or structural grids, remains a significant challenge for current segmentation models, including the Segment Anythin…
LEG-SLAM: Real-Time Language-Enhanced Gaussian Splatting for SLAM
Roman Titkov, Egor Zubkov, Dmitry Yudin +3
Modern Gaussian Splatting methods have proven highly effective for real-time photorealistic rendering of 3D scenes. However, integrating semantic information into this representati…
DyGEnc: Encoding a Sequence of Textual Scene Graphs to Reason and Answer Questions in Dynamic Scenes
Sergey Linok, Vadim Semenov, Anastasia Trunova +2
The analysis of events in dynamic environments poses a fundamental challenge in the development of intelligent agents and robots capable of interacting with humans. Current approac…