Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Augmented Vision

non-profit
https://av.dfki.de
dfki-av
Activity Feed Request to join this org

AI & ML interests

Our core research topics range from visual analysis, including detection and tracking of objects in video sequences, over 3D computer vision, including 3D reconstruction of environments, objects and human body shapes, to motion, activity and workflow capture based on on-body and external networks of cameras, inertial and bio sensors.

Papers

NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling

Towards Unconstrained 2D Pose Estimation of the Human Spine

View all Papers

Muhammad Saif Ullah Khan's profile picture René Schuster's profile picture Muhammad Usama's profile picture Mohammad Sadil Khan's profile picture Sai Srinivas Jeevnandam's profile picture Mahdi Chamseddine's profile picture Jason Rambach's profile picture
dfki-av 's Papers 6
Submitted by
Mohammad Sadil Khan
13

NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling

dfki-av Augmented Vision
5 2
-

Towards Unconstrained 2D Pose Estimation of the Human Spine

dfki-av Augmented Vision
20
Submitted by
Mohammad Sadil Khan
26

MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation

dfki-av Augmented Vision
3 7
-

Classroom-Inspired Multi-Mentor Distillation with Adaptive Learning Strategies

dfki-av Augmented Vision
0
5

Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts

dfki-av Augmented Vision
359 3
-

SituationalLLM: Proactive language models with scene awareness for dynamic, contextual task guidance

dfki-av Augmented Vision
0
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs