Hi, I'm Anand !

I am a Computer Vision Engineer at Toothlen Inc. where I am building the next generation of VIT,MMDIT models for medical imaging.

Learn more

Highlights

Finalist – Smart India Hackathon 2022 (Surveillance System using Computer Vision) along with my teammate Amit Yadav
Winner – Project Development Skills Hackathon 2022 for creating Virtual Board software (team project with Amit Yadav)
Best Research Paper Award – The Art of 3D Scene Understanding: Implementing and Enhancing Neural Radiance Fields, TECH-SPARDHA NIET Conference, 2023 (Oral Presentation) [Project Page] (co-authored and presented with Amit Yadav)

Work Experience

Summer 2022: I interned at Microsoft Future Ready Talent where I worked on the project Flight Price Prediction. Project Page

Publications

Shape-Guided Conditional Image Synthesis for Tooth Alignment, IJSET, 2024
Recognition of Sentiment using Deep Neural Network, IJTSRD, 2023

Projects

Chat-with-PDF (Local RAG) – Built with Ollama + DeepSeek-R1:1.5B for local document Q&A.
Virtual Try-On API – Diffusion (Flux) + LoRA with Flash Attention on RTX 4090. (Ref)
Video-based Generation (MM-DiT) – Exploring multimodal transformer-based architectures.
AI Drawing Tool – Hands-free drawing using OpenCV + NumPy.
Human Action Recognition – ConvLSTM + LRCNN models, 82% accuracy.
Healthcare Chatbot – Flask chatbot for women’s health, fine-tuned with LLaMA2.
Synthetic Data Generation – Created synthetic datasets for training and evaluation of vision models.
High-Precision Visual Analysis – Integrated PyTorch, OpenCV, Fast R-CNN, YOLO, Matplotlib, and Vision Transformers.
Medical Imaging Tools – Applied segmentation and enhancement pipelines to dental/medical datasets.

Skills

AI/ML/DL: Computer Vision, Diffusion Models, Transformers, LoRA

Programming: Python, Bash

Tools: PyTorch, TensorFlow, Flask, OpenCV, Hugging Face

Cloud: AWS (EC2, deployment, analysis)

Additional Skills

Diffusion models
Stable Diffusion
Object Detection
Instance Segmentation
Semantic & Panoptic Segmentation
Conditional Image Generation
Image Enhancement
MLOps
Medical Imaging
Nginx
Ngrok
fiftyone
NeRF
Synthetic Data Generation

I've implemented high-precision visual analysis and object detection systems by integrating advanced tools and frameworks, including PyTorch, OpenCV, Fast R-CNN, YOLO, Matplotlib, and Vision Transformers.