MaSceneGraphs

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Scene graph generation

We are looking for a motivated student to work on a research topic that involves deep learning and scene understanding. The project consists on generating scene graphs, which is a compact data representation that describes an image or 3D model of a scene. Each node of this graph represents an object, while the edges represent relationships/interactions between these objects, e.g. "boy - holding - racket" or "cat - next to - tree". The application of scene graphs involve image generation, content-based queries for image search, and sometimes serve as additional context to improve object detection accuracy.

Example scene graph of an image:

source: Xu et al. Scene Graph Generation by Iterative Message Passing. CVPR 2017

Prerequisites: The candidate should have interest and a good understanding for graph structures, deep learning knowledge, be comfortable with Python, and preferably have some basic experience with a deep learning framework, such as PyTorch?. Last but not least - a good motivation to work on challenging and new ideas.

Preferably master thesis. Also possible as guided research.

Supervision: Helisa Dhamo, PD Dr. Federico Tombari

Please drop an email to Helisa Dhamo if you want to find out more.

ProjectForm
Title: Scene graph generation
Abstract: We are looking for a motivated student to work on a research topic that involves deep learning and scene understanding. The project consists on generating scene graphs which is a compact data representation that describes an image or 3D model of a scene. Each node of this graph represents an object, while the edges represent relationships/interactions between these objects, e.g. "boy - holding - racket" or "cat - next to - tree". The application of scene graphs involve image generation content-based queries for image search, and sometimes serve as additional context to improve object detection accuracy. Preferably master thesis. Also possible as guided research.
Student:  
Director: Federico Tombari
Supervisor: Helisa Dhamo
Type: Master Thesis
Area: Machine Learning, Computer Vision
Status: running
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.2 - 22 Apr 2020 - 12:27 - HelisaDhamo