baranekin Goto Github PK

autonomous-driving-sim

Camera vision based Autonomous Driving DL Agent in a simulated 3D city. Agent uses ResNet-based NN trained on simulator data for steering control and pretrained Faster R-CNN for vehicle detection

baranekin

bevblip

Efficient and lightweight Vision-Language model for Visual Question Answering in autonomous driving scenarios. The approach replaces images in BLIP's architecture with spatio-temporal BEV feature maps

bevformer

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

blip

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

change-detection

Self-supervised Change Detection in SAR Images via Single Image Height Estimations

drivelm

DriveLM: Driving with Graph Visual Question Answering

jungle-watch

ResNet50 based CNN trained using PyTorch, for classification of animals in wildlife from images captured by camera traps

to-born-or-not-to-born

Analysis and classification on 2018 US Birth data

voxel-carving-with-aruco

3D Reconstruction of objects from multiple images on top of ArUco markers, using voxel carving algorithm.