Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park*, Rares Ambrus*, Vitor Guizilini, Jie Li, and Adrien Gaidon.

This is a Multi object tracker. Mainly it was build for tracking car movement in a junction.

Simple model to Track and Re-identify individuals in different cameras/videos.(Yolov3 & Yolov4)

Source Code of our CVPR2021 paper "Rethinking BiSeNet For Real-time Semantic Segmentation"

Google Research

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

Single-View Auto-Calibration from Lens-Distorted Images of Urban Scenes. In WACV (2021)

TRI-ML Monocular Depth Estimation Repository

A repo of awesome papers about multi target multi camera tracking

Code for ICCV2021 paper SPEC: Seeing People in the Wild with an Estimated Camera

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

MVSNet: Depth Inference for Unstructured Multi-view Stereo using pytorch-lightning

Few-shot Object Detection via Feature Reweighting

Vehicle Speed Check

This is a Python + OpenCV implementation of the Vanishing Point algorithm by Xiaohu Lu et al. - http://xiaohulugo.github.io/papers/Vanishing_Point_Detection_WACV2017.pdf

[ICCV'21] UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

Official implementation of the paper: MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera (CVPR 2021)

COLMAP - Structure-from-Motion and Multi-View Stereo

A multi-camera vehicle detection, tracking and re-identification system

The code from the top teams in the 2021 AI City Challenge (not in any particular order)

Multi-view 3D reconstruction using neural rendering. Unofficial implementation of UNISURF, VolSDF, NeuS and more.

Implementation for paper: "Detection of 3D bounding boxes of vehicles using perspective transformation for accurate speed measurement"

[ICCV 2019] Monocular depth estimation from a single image

Code for "Convolutional Generation of Textured 3D Meshes", NeurIPS 2020

Depth-Aware Video Frame Interpolation (CVPR 2019)

⚡ Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and …

Pytorch codes for "Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation"