SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment
arXiv, 2025
SGAligner++ is a 3D scene graph alignment framework across modalities using open-vocabulary cues and learned joint embeddings.
Binod Singh
PhD Student · Technical University of Denmark (DTU)
I am a PhD student at the Technical University of Denmark (DTU), advised by Prof. Theodora Kontogianni. Before that, I worked with Prof. Iro Armeni and Sayan Deb Sarkar in the Gradient Spaces Group at Stanford University, and I received my master's degree from the Technical University of Munich.
I work at the intersection of 3D vision and 3D scene understanding, focusing on multimodal data representations for interpreting complex 3D environments.
I am always open to research collaborations and happy to connect. Feel free to reach out!
Publications
Academic Services
Teaching
- Teaching Assistant, Introduction to Deep Learning in Computer Vision · DTU · 2026