4 papers
Modernising Reinforcement Learning-Based Navigation for Embodied Semantic Scene Graph Generation
Roman Küble, Marco Hüller, Mrunmai Phatak +2
Semantic world models enable embodied agents to reason about objects, relations, and spatial context beyond purely geometric representations. In Organic Computing, such models are…
DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtime
Julian Lorenz, Vladyslav Kovganko, Elias Kohout +3
Scene Graph Generation (SGG) aims to extract a detailed graph structure from an image, a representation that holds significant promise as a robust intermediate step for complex dow…
CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations
Julian Lorenz, Mrunmai Phatak, Robin Schön +4
2D scene graphs provide a structural and explainable framework for scene understanding. However, current work still struggles with the lack of accurate scene graph data. To overcom…
HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactions
Mrunmai Vivek Phatak, Julian Lorenz, Nico Hörmann +2
When humans and robotic agents coexist in an environment, scene understanding becomes crucial for the agents to carry out various downstream tasks like navigation and planning. Hen…