Balamurugan Thambiraja

About Me

Hi! I’m Balamurugan Thambiraja, presently pursuing a PhD at the Neural Capture and Synthesis group of Prof. Justus Thies at the Max-Planck Institute for Intelligent Systems, Germany. During my Ph.D., I'm collobrating with Darren Cosker and Sadegh Aliakbarian from Mesh Labs, Microsoft, Cambrdige.

In my Ph.D. im focusing on human motion and its associated dynamics. Recently, I have been exploring the potential use of diffusion-models and large-language-models for motion synthesis and editing. In general, I'm interested in the temporal dimension, particularly on how things change and evolve over time. I aim to improve video synthesis and our comprehension of video information.

Before the PhD, I did a Masters in Informatics at TUM, Germany, where I worked on human modelling and sign language synthesis at the Visual Computing and Artificial Intelligence group of Prof. Matthias Niessner . Before that, I did my Bachelors in Electrical and Electronics Engineering at Kumaraguru College of Technology, Coimbatore, India.

Research

3DiFACE: Synthesizing and Editing Holistic 3D Facial Animation

3DiFACE is a novel diffusion-based method for synthesizing and editing holistic 3D facial animation from an audio sequence, wherein one can synthesize a diverse set of facial animations and seamlessly edit facial animations.

View Project

ICCV 2023

Imitator: Personalized Speech-driven 3D Facial Animation

Imitator is a novel method for personalized speech-driven 3D facial animation. Given an audio sequence and a personalized style-embedding as input, we generate person-specific motion sequences with accurate lip closures for bilabial consonants ('m','b','p'). The style-embedding of a subject can be computed by a short reference video (e.g., 5s).

View Project

Master Thesis

Neural Sign Language Synthesis

We present a novel method to synthesize sign pose sequences from input text using a transformer-based method. We achieved state-of-the-results in RWTH-PHOENIX 2014T benchmark by utilizing relative positional embedding and relative patch discriminator.

Thesis(pdf) Presentation(pptx)

Experience

May 2021 – August 2021

Presize GmbH(now Meta), Munich, Germany

Deep Learning Intern

Worked on the online real-time virtual try-on system. Designed and developed a novel FLOW-based virtual try-on method.

September 2020 – March 2021

Research Neutron Source Heinz Maier-Leibnitz, Germany

Student Research Assistant - CUDA Developer

Developed image processing and computer vision algorithms in CUDA for neutron imaging.

October 2019 – June 2020

Osram Automotive GmbH

AI/CV Student Researcher

Worked on real-time head pose and eye gaze estimation for driver awareness monitoring system. Contributed to development of the eye gaze tracking solution that can run real-time on edge-computing devices.

July 2015 – August 2017

Wirecard India Private Limited

Software Analyst

At Wirecard, I worked on prepaid card application platform called NARADA and CORECARD, where I mainly worked on automating manual tasks using Python, VB Scripts, RUNDECK and Shell Scripts.