4 papers
From Scan to Action: Leveraging Realistic Scans for Embodied Scene Understanding
Anna-Maria Halacheva, Jan-Nico Zaech, Sombit Dey +2
Real-world 3D scene-level scans offer realism and can enable better real-world generalizability for downstream applications. However, challenges such as data volume, diverse annota…
Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description
Anna-Maria Halacheva, Yang Miao, Jan-Nico Zaech +3
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 t…
GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond
Anna-Maria Halacheva, Jan-Nico Zaech, Xi Wang +2
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…
Expanding Expressivity in Transformer Models with MöbiusAttention
Anna-Maria Halacheva, Mojtaba Nayyeri, Steffen Staab
Attention mechanisms and Transformer architectures have revolutionized Natural Language Processing (NLP) by enabling exceptional modeling of long-range dependencies and capturing i…