docs/biography.txt

Prakash Naikade
Computer Vision & Machine Learning Engineer

PROFILE
I am passionate about Machine Learning, especially Computer Vision and Generative AI. I have hands-on experience
from academia and industry. My research interests span in the broad areas of 3D-Reconstruction, Scene Understanding, 
Neural Rendering, Radiance Field, Motion Capture, Digital Twins, LLMs, AR/VR, and generally Computer Vision,
Computer Graphics, GenAI, Human Computer Interaction, Deep Learning, Machine Learning, and Data Science, to
solve real-world problems with impactful AI aided solutions.

EDUCATION
Masters in MSc Media Informatics at Saarland University, Germany
Oct 2020 – Present
Grade: 1.6/5.0 (1.0 being the best possible score) 
Thesis: Novel View Synthesis of Structural Color Objects Created by Laser Markings. (1.3)
Relevant Courses: Computer Graphics, Image Processing & Computer Vision, Neural Networks: Theory & Implementation, 
High-Level Computer Vision, Statistics with R, Adversarial Reinforcement Learning, Human Computer Interaction,
Games & Interactive Media. 
[Audited]: Geometric Modeling, Machine Learning, AI, Ethics for Nerds

Bachelor of Engineering in Computer Engineering at Pune University, India
June 2011 – May 2015
Grade: 65% (First Class) 
Thesis: Secure Data Storage on Multi-Cloud Using DNA Based Cryptography.
Relevant Courses: Data Structures and Algorithms, Design & Analysis of Algorithms, Software Architecture, Software
Engineering, Software Testing & Quality Assurance, Microprocessors & Microcontrollers

PROFESSIONAL EXPERIENCE
Junior Researcher (HiWi) Saarbrücken, Germany
August-Wilhelm Scheer Institute 
Sept 2023 – Dec 2024
• Worked on several applied research projects, including MediHopps, iperMö, FläKI and VuLCAn.
• Implemented advanced deep learning methods for human action recognition (HAR) and body pose estimation (HPE),
and delivered detailed performance evaluations of these models, along with a trained HAR model (ST-GCN++) for
custom rehabilitation exercise data captured in the lab.
• Contributed significantly to the feature extraction, generation, and visualization of furniture functionalities in the
Python codebase for the iperMö project, developing an AR application to turn individual furniture wishes into reality.
• Systematic Literature Research and Reviews, Project Proposals and Scientific Literature Writing.
• Generally worked on computer vision, computer graphics, and machine/deep learning tasks like human pose esti-
mation, human action recognition, and some XR tasks.

Research Assistant Saarbrücken, Germany
AIDAM, Max Planck Institute for Informatics Advisor: Dr Vahid Babaei 
July 2023 – Aug 2024
• Worked on Radiance Field methods for Novel View Synthesis of structural color objects created by laser markings.
• Benchmarked SOTA radiance methods for synthetic scene involving Structural Color Object created in Blender.
• Developed capture setup to capture highly reflective and shiny structural color paintings on metal substrates.
• Improved the scene optimization using geometric prior and Anisotropy Regularizer in 3D Gaussian-Splatting method.
• Presented comprehensive experiments to demonstrate methods for simulating structural color objects before printing
them using only captured images of laser-printed primaries.
• Facilitated interactive visualization of view-dependent structural color objects in web viewer.

Computer Vision Intern Münster, Germany
BASF-Coatings GmbH 
March 2023 – May 2023
• Developed dataset for adhesive test and corrosion detection on images of test panels of metal substrates.
• Developed framework and trained YOLOv8 model for adhesive tests’ detection and UNet for corrosion detection
using created dataset for automation project.

Computer Vision Intern Aachen, Germany
Fenris GmbH 
May 2022 – Sept 2023
• Contributed to markerless motion capture solutions using single and multiple cameras for athlete motion tracking
and analysis.
• Conducted a comprehensive literature research and review focused on deep learning approaches for human pose
estimation and benchmarked SOTA approaches for domain specific video data.
• Worked on different tasks such as camera calibration, deep learning based human pose estimation & golf sequence
detection, estimating joint angles from 3D body poses, comparing two pose sequences and visualization of results
in Blender and Unity.

Indian Civil Services Exam Preparation 
Jun 2015 – July 2019
During the preparation of this exam, I gained Under-Graduate level knowledge of Anthropology, Polity, Governance,
Indian Constitution, Social Justice, International Relations, Economics (Macro), Indian & World Geography, Indian &
World History, Indian Culture & Society, Environment, and Ethics. (Overall pass percentage of candidates ≈ 0.1%)

SKILLS
• Programming: Python, C#, C++, R, SQL, Matlab
• Frameworks: PyTorch, TensorFlow, NumPy, Pandas, SKLearn, OpenCV, Open3D, Matplotlib, HuggingFace
• Tools: Conda, Jupyter Notebook, Git, Unity, Blender, Metashape, Colmap, Meshlab, Docker, Slurm/HPC, DevOps
• OS: Linux, Windows, Shell/Dos Scripting
• Concepts: Regression, k-NN, k-Means Clustering, PCA, SVM, Neural Networks, CNN, RNN, LSTM, Transformers,
ViT, CLIP, Autoencoders, VAE, GAN, Diffusion Models, LLMs, NLP, GPT, Prompt Engineering, LangChain, 2D/3D
Image Processing, Object Detection, Classification, Localization, Segmentation, NeRF, 3DGS, 3D Reconstruction,
Scene Understanding, Scene Interaction, HCI, XR, Reinforcement Learning

PROJECTS
Learn-LLMs GenAI, Information Retrieval
Getting a hands-on experience of using different LLM models and tools, to understand the finetuning, data preparation,
evaluation & other techniques related to LLMs such as RAG.

Diffusion Models Computer Vision, GenAI
This Project is a basic implementation of Diffusion Model to understand how diffusion works.

Human Action Recognition (HAR) Computer Vision
Investigating the performance of different deep learning models and their ensembles used for HAR in still images.

Image Segmentation on PASCAL VOC and Cityscapes Datasets Computer Vision
Training and Evaluation of CNNs like UNet, RU-Net and R2U-Net for Image Segmentation.

COVID-19 Detection Computer Vision
TensorFlow implementation of model based on ResNet50 architecture for COVID-19 detection on Chest X-rays using
dataset sourced from Kaggle.

Object Detection Computer Vision
Training an object detection model on custom dataset (Oxford Pets dataset) using TensorFlow Object Detection API 2.

Easy Flappy Bird Game Development
An simple implementation of Flappy Bird game using Unity and C#.

Roman Villa Nennig Bot - Your virtual guide to Roman Villa Nennig NLP
This chatbot helps the user throughout their journey of visiting a museum of the Roman Villa Nennig, developed using
Google Cloud, Dialogflow Essentials and Telegram.

Ludwig Palette - an AR painting game AR/VR
App developed in Unity and C# allows visitors of Ludwigskirche to explore its architecture by painting on its surfaces
and understand the intricacies of sculptures inside the church.

Mini-RayTracer Computer Graphics
Simple ray tracing engine developed in C++.

Synthetic Dataset Computer Graphics
Generate simple 3D rendered datasets in Blender and Unity.

PUBLICATIONS
• Secure Data Storage on Multi-Cloud Using DNA Based Cryptography. D Zingade, S Dhuri, P Naikade, N Gade,
A Teke, International Journal of Advance Engineering and Research Development March 2015

CERTIFICATIONS
• Kaggle: Python, ML, Pandas, Feature Engineering, Data Visualization, Data Cleaning, SQL, Reinforcement Learning
& Game AI, Time Series
• Udacity: C++, AWS ML Foundations
• Coursera: Mathematics for Machine Learning and Data Science, Structuring ML Project, Neural Network and Deep
Learning, Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization
• Udemy: Foundations of MR, XR, VR Development on Quest headsets with Meta’s Presence Platform and Unity.
• DataCamp: Intermediate R, Data in R
• Memgraph: Graph Analytics

LANGUAGES
English (Fluent), Hindi (Fluent), Marathi (Native), German (Elementary)

HOBBIES
Biking, Running, Hiking, Movies, Music