Type: User
Company: CentraleSupelec / Paris Saclay Univesity
Bio: Computer Vision Research Engineer:
SFM,
Visual Localization,
3D Reconstruction,
Scene Parsing,
Deep Learning,
Location: Paris
Blog: https://tarekbouamer.github.io/
tarekbouamer's Projects
code for Mesh R-CNN, an academic publication, presented at ICCV 2019
3D Reconstruction Software
Official code for Modeling the Background for Incremental Learning in Semantic Segmentation https://arxiv.org/abs/2002.00718
Matchable Image Retrieval by Learning from Surface Reconstruction
Tools for evaluating and visualizing results for the Multi Object Tracking and Segmentation (MOTS) task
A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning
A PyTorch port of the Neural 3D Mesh Renderer
Neural Point-Based Graphics
Implementation of ICCV19 Paper "Learning Two-View Correspondences and Geometry Using Order-Aware Network"
PopSift is an implementation of the SIFT algorithm in CUDA.
Code for Deep Surface Normal Estimation with Hierarchical RGB-D Fusion (CVPR2019)
Seamless Scene Segmentation
Efficient neural feature detector and descriptor
This game is a simple platofrmer game made as part of the Game Development for Modern Platforms course. the game contain 10 levels. each level contains enemies and obstacles and you objective is to move and jump until you collect the win item (Red Rose).
Code for CVPR 2018 paper "Hashing as Tie-Aware Learning to Rank"
TrackR-CNN baseline method for Multi-Object Tracking and Segmentation (MOTS)
Official codebase for Pretrained Transformers as Universal Computation Engines.
I have been follwing this course as reference to build a strong background in Computer vision fro Autonomous sytems such as feature extraction, multiple view geometry, dense reconstruction, tracking, image retrieval, event-based vision, and visual-inertial odometry.