This repository includes Pytorch implementation of semantic segmentation on aerial image of drone dataset.

Project to recognize STAR presence in an image and build a bounding box around it, if identified

Predicting cats feature points using a feature pyramid network

An implementation for fpn network with mxnet

Improve performance of PWC-Net in foggy scenes

Object Detector for Autonomous Vehicles Based on Improved Faster-RCNN

Website of "FILM: Frame Interpolation for Large Motion", In ECCV 2022.

Digital Video Processing Graduate Course Homeworks

Project on the implementation of deep-learning models for ship detection on SAR images.

This is a capstone project on a real dataset related to segmenting low-grade glioma. This capstone project is included in the UpSchool Machine Learning & Deep Learning Program in partnership with Google Developers.

The SFPN is a novel plug-and-play component for the CNN object detector. This project is the official code for the paper "SFPN: Synthetic FPN for Object Detection" in IEEE ICIP 2022.

Feature Pyramid Network based on VGG16 and ResNet101

(IEEE TIP 2021) Regularized Densely-connected Pyramid Network for Salient Instance Segmentation

PyTorch implementations of some FPN-based semantic segmentation architectures: vanilla FPN, Panoptic FPN, PANet FPN; with ResNet and EfficientNet backbones.

DETR - Faster RCNN implementation in tensorflow 2

Motion R-CNN: Mask R-CNN with support for 3D motion estimation (prototype)

[ECCV 2024] Pytorch code for our ECCV'24 paper NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields

Experiments with UNET/FPN models and cityscapes/kitti datasets [Pytorch]