Fabian Perez
AI researcher, i like to train deep neural nets 🧠🤖
About
I am a computer science student at Universidad Industrial de Santander (UIS) in Colombia. I am currently a master student in computer science. I have strong skills in software development and deep learning. My expertise across both these areas allows me to create innovative solutions by bringing them together
Education
Universidad Industrial de Santander
University of Delaware
King Abdullah University of Science and Technology
Universidad Industrial de Santander
Interests
Recent Highlights
- July 2025: 🚀 Excited to share that our paper "UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields" has been accepted to ICCV 2025!
- June 2025: Our team at Hands-on Computer Vision won first place 🥇 in the SoccerNet Monocular Depth Estimation Challenge, presented at the CVSports Workshop during CVPR 2025.
- June 2025: Selected for the University of Delaware Summer Research Program under the mentorship of Prof. Gonzalo Arce.
- February 2025: Started my Master's in Computer Science under the supervision of Prof. Hoover F. Rueda.
- December 2024: Graduated with a Bachelor's degree in Computer Science.
- October 2024: Presented and defended my undergraduate thesis, which received honors (laureated).
- September 2024: Started a Research Internship at King Abdullah University of Science and Technology (KAUST), working on 3D Hyperspectral Imaging.
- July 2024: Our paper "Beyond Appearances: Material Segmentation with Embedded Spectral Information from RGB-D imagery" was accepted at CVPR 2024 LatinX Workshop.
Papers
UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields
Fabian Perez, Sara Rojas Martinez, Carlos Hinojosa, Hoover Rueda-Chacón, Bernard Ghanem
UnMix-NeRF integrates spectral unmixing with NeRFs to enable simultaneous hyperspectral view synthesis and unsupervised material segmentation. Unlike traditional NeRFs that rely solely on RGB, our approach captures the intrinsic spectral properties of materials, allowing precise material segmentation and scene editing.
Beyond Appearances: Material Segmentation with Embedded Spectral Information from RGB-D imagery
Fabian perez, Hoover Rueda-Chacon
Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning
Fabian perez, Jhon Lopez, Henry Arguello
we propose a novel Privacy-Preserving framework that uses a set of deformable operators for secure task learning. Our method involves shuffling pixels during the analog-to-digital conversion process to generate visually protected data
Projects
Lineas Hospitalarias web
A platform for the management of products and services of the entity
SkyWatch App
An app for the control of the personal and the devices installed by the company
Segmentation of wounds
A project for the segmentation of wounds in images
Image stitching with superglue
Robust image stitching that leverages advanced feature matching techniques to achieve high-quality results
Spotify song recommender
Spotify song recommendation system based on music tastes
Google Translate Dark theme
A custom dark theme for Google Translate webpage
Awards
Yipao
Revolutionizing business intelligence with AI-driven SQL interactions. Simplify complex queries and enhance database efficiency effortlessly
Hunter
Artificial Intelligence model-as-a-service tool that facilitates the process of facilitates the process of recruitment and human talent management in companies, and companies,
DeepBeauty
My favorite hackathon, a deep learning model for automatic semantic segmentation for aerial imagery in Bucaramanga
