← Search

Anna-Maria Halacheva

2 accepted papers

2026

GaussianVLM: Scene-Centric 3D Vision-Language Models Using Language-Aligned Gaussian Splats for Embodied Reasoning and Beyond

ICRA 2026poster

As multimodal language models advance, their application to 3D scene understanding is a fast-growing frontier, driving the development of 3D Vision-Language Models (VLMs). Current methods show strong dependence on object detectors, introducing processing bottlenecks and limitations in taxonomic flex…

2025

Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description

ICCV 2025poster

3D scene understanding is a long-standing challenge in computer vision and a key component in enabling mixed reality, wearable computing, and embodied AI. Providing a solution to these applications requires a multifaceted approach that covers scene-centric, object-centric, as well as interaction-cen…

Cited by 0SourcePDFScholar