Shriarulmozhivarman G C
Computer Vision Researcher
PhD Candidate in Computer Vision
Research Interests
Exploring spatial AI models that leverage joint appearance and geometric cues for advanced computer vision applications, including salient object detection, multi-sensor fusion, and robotics perception.
Work Experience
Doctoral Candidate
Austrian Institute of Technology
Mar., 2023 - Present
Vienna, Austria
Topic: Spatial AI model learning by exploiting joint appearance and geometric cues
Research Internship
Imagerie et Vision Artificielle (ImViA) University of Burgundy
Feb., 2022 - Jul., 2022
Dijon, France
Supervisor: Prof.Dr. Cédric Demonceaux
Topic: RGB-Depth Fusion for Salient Object Detection
Computer Vision Internship
Imagerie et Vision Artificielle (ImViA) University of Burgundy
Jul., 2021 - Sep., 2021
Le Creusot, France
Robotics Internship
Ingeniarius
Jul., 2018 - Sep., 2018
Coimbra, Portugal
Education
Doctoral Programme in Computer Sciences (PhD)
Vienna University of Technology
Jul., 2023 - Present
Vienna, Austria
Specialization: Computer Vision
Masters of Science - Computer Vision
University of Burgundy
Sep., 2020 - Sep., 2022
Le Creusot, France
Specialization: Vision and Robotics
Thesis: Robust RGB-Depth images Fusion for Salient Object Detection
Bachelor of Science - Mechatronics
Vilnius Tech
Sep., 2015 - Jun., 2019
Vilnius, Lithuania
Specialization: Mechatronics and Robotics
Thesis: Design Of Collaborative Indoor Robots
My Projects
Robust RGB-Depth Fusion for Saliency Detection
Combining RGB and depth information for accurate salient object detection. Achieved improved accuracy in challenging scenarios.
View on GitHub →Spatial AI Model Learning
Developing AI models exploiting appearance and geometric cues for spatial understanding.
View on GitHub →Design of Collaborative Indoor Robots
Thesis on design principles for robots in collaborative indoor tasks.
View on GitHub →Publications
Robust RGB-D Fusion for Saliency Detection (Poster)
10th International Conference on 3D Vision
Sep., 2022
Prague, Czech Rep.
Deployed Hugging Face space of the paper. View Space
Achievements
- 15th Batch of International Programme in VIsion roBOTics (VIBOT)
- Best Student of the Year 2020 - 2022
Skills and Ability
Programming Languages:
- Python
- Matlab
Machine Learning Tools:
- PyTorch
- Sklearn
- Tensorflow
- PyTorch Lightning
Computer Vision Tools:
- OpenCV
- PIL
- Matlab Image Processing Toolbox
Operating Systems:
- Linux
- ROS
- ROS2
Hardware Tools:
- Arduino
- Raspberry Pi
- Jetson Devices
CI/CD Tools:
- Git
- Git Actions
- Docker
- Streamlit
- Gradio
Languages:
- Tamil-Native
- English-C1