MobileNets-SSD/SSDLite on VOC/BDD100K Datasets

Image2Image Translation Research

My Computer Vision project from my Computer Vision Course (Fall 2020) at Goethe University Frankfurt, Germany. Performance comparison between state-of-the-art Object Detection algorithms YOLO and Faster R-CNN based on the Berkeley DeepDrive (BDD100K) Dataset.

Faster R-CNN with KITTI, BDD100k support in PyTorch 1.0

Open source training framework for vision tasks. Scales up on data and scales up on tasks. Official Implementation for https://arxiv.org/abs/2310.00920

Pytorch implementation of DeepLab V3+

[WACV 2025] Official implementation of "RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation"

This repository contains the implementation of a lane detection system using the UNet architecture. The model is trained on the BDD100K dataset, leveraging its diverse and large-scale data to ensure robust performance under various weather conditions and different times of day.

Training FCOS on KITTI and BDD100K datasets for real-time traffic object detection with PyTorch.

Road Object Detection using Deep Learning, based on tensorflow framework and BDD100k dataset

University of Bristol MEng Computer Science Dissertation and Code for 'Predicting Ego-Vehicle Speed from Monocular Dash-Cam Video in Diverse Conditions'.

Code for paper: "Road object detection: a comparative study of deep learning-based algorithms" https://link.springer.com/article/10.1007/s11042-022-12447-5

Perform inference with TwinLiteNet model using ONNX Runtime. TwinLiteNet is a lightweight and efficient deep learning model designed for drivable area and lane segmentation

The official code open source version of BFDA - based on YOLOv5

A data visualization tool for the Berkley Deep Drive Dataset (available as a Plotly-Dash webapp or TKinter GUI app)

Object detection model for BDD100K

RWVC-BDD100K is a set of image-level annotations on road, weather and visibility condition for a large number of examples from the BDD100K dataset.

Some benchmarks and easy-to-understand explanations for the BDD100K dataset in MaskFormer.

An easy-to-use implementation for performing inferencing with TwinLiteNet model using OpenCV DNN module. TwinLiteNet is a lightweight and efficient deep learning model designed for drivable area and lane segmentation

Project work part of Deep Learning Course at Clemson University.