Home

Contact me

Computer Vision

My specialisation lies in gathering insights from visual data, spanning object detection and recognition, image segmentation, and automated image manipulation.

Grounded in formal education, years of interest, and an ongoing exploration, I stay at the forefront of research, ensuring deep understanding and practical applications of computer vision across diverse domains.

A small selection of my work

Fragment

Fragment is a one-stop-shop to convert videos into photorealistic 3D models with computer vision and machine learning.

Under the hood, the 3D model reconstruction is powered by customised NeRF models, with help of several segmentation networks to clean up unwanted objects.

I built Fragment from the ground up: Frontend with in-browser renderer using React and Three.js, and backend with ML models using Python.

VISIT
Fragment image

All Axis

All Axis creates interactive 3D product photos that are simple to integrate on any website.

I have an ongoing collaboration with All Axis. I built a custom pipeline to convert unstructured photos into a photorealistic 3D model and renders novel images using a custom Gaussian Splatting solution. Additionally, I implemented a suite of internal tools to modify and edit the generated gaussian splats.

After the model is processed, it can be displayed just about anywhere or used to generate additional product photos.

VISIT

Sudoku Solver

Sudoku is a popular logic-based puzzle where the objective is to place numbers in 9x9 grid.

Visual sudoku solver captures a sudoku puzzle through computer’s webcamera. Once the puzzle is detected, the program attempts to solve it and displays the solution as an overlay over the original video feed.

To build this app, I used Tensorflow, OpenCV, and Python.

VISIT
Sudoku image

Interested in working together?

Get in touch at hello@martinpiala.com or find me on LinkedIn.

© 2024 Martin Piala. All rights reserved.