Sankalp Sinha

E-Mail:	Sankalp.Sinha@dfki.de
Position:	Researcher

About:

Hey, stranger 👋,

I work at the intersection of vision, language, and geometry—building AI systems that can see, understand, and create. My research spans multimodal learning, 3D visual understanding, retrieval systems, and document intelligence. I’m particularly interested in how language can be used to solve visual problems—whether through guiding perception, enabling generation, or improving retrieval. I focus on building models that operate across different modalities and tasks, supported by scalable data pipelines and strong underlying representations.

5 Publications by Sankalp Sinha:

MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation
Sankalp Sinha, Mohammad Sadil Khan, Muhammad Usama, Shino Sam, Didier Stricker, Sk Aziz Ali, Muhammad Zeshan Afzal
In: In Proceedings of the Forty-Second Annual Conference on Computer Vision and Pattern Recognition (CVPR-25). International Conference on Computer Vision and Pattern Recognition (CVPR-2025), June 11-15, Nashville, Tennessee, USA, IEEE/CVF, 2025.
Details | Link 1

Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts
Mohammad Sadil Khan, Sankalp Sinha, Talha Uddin Sheikh, Didier Stricker, Sk Aziz Ali, Muhammad Zeshan Afzal
In: The Thirty-Eighth Annual Conference on Neural Information Processing Systems. Neural Information Processing Systems (NeurIPS-2024), December 10-15, Vancouver, British Columbia, Canada, Pages 7552-7579, Vol. 37, Neural Information Processing Systems, 1/2025.
Details | Link 1

Shape2.5D: A Dataset of Texture-less Surfaces for Depth and Normals Estimation
Muhammad Saif Ullah Khan, Sankalp Sinha, Didier Stricker, Marcus Liwicki, Muhammad Zeshan Afzal
In: IEEE Access (IEEE), Vol. 12, Pages 1-1, IEEE, 11/2024.
Details

CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification
Sankalp Sinha, Muhammad Saif Ullah Khan, Talha Uddin Sheikh, Didier Stricker, Muhammad Zeshan Afzal
In: ICDAR 2024 Main Conference Proceedings. International Conference on Document Analysis and Recognition (ICDAR-2024), 18th International Conference on Document Analysis and Recognition, located at International Conference on Document Analysis and Recognition, August 30 - September 4, Athens, Greece, Springer, 2024.
Details | Link 1

Rethinking Learnable Proposals for Graphical Object Detection in Scanned Document Images
Sankalp Sinha, Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal
Applied Sciences (MDPI) 12 20 Seiten 1-22 MDPI Switzerland 10/2022 .
Details | Link 1 | Link 2