thejasonfisher

ffmpegcv

The ffmpegcv is a ffmpeg backbone for open-cv like Video Reader and Writer

python-rtsp-server

Lightweight, zero-dependency proxy and storage RTSP server

yolov8-digits-detection

Digits detection with YOLOv8 detection model and ONNX pre/post processing

DALI

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

deepstream-yolo-pose

Use Deepstream python API to extract the model output tensor and customize the post-processing of YOLO-Pose

Dynamic3DGaussians

edgeai-yolox

YOLOX-ti-lite models are optimized for deployment on TI edge processors

fastai

The fastai deep learning library

gradslam

gradslam is an open source differentiable dense SLAM library for PyTorch

hawp

Holistically-Attracted Wireframe Parsing [TPAMI'23] & [CVPR' 20]

LightGlue

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

lightning-flash

Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains

LoFTR

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

MiDaS

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

MixSort

[ICCV2023] MixSort: The Customized Tracker in SportsMOT

oddgen

Generate object detection datasets from individual objects with automatic bounding box annotations

One-Style-is-All-You-Need-to-Generate-a-Video

Conditonal video generation with style

pyskl

A toolbox for skeleton-based action recognition.

redis-product-search

Visual and semantic vector similarity with Redis Stack, FastAPI, PyTorch and Huggingface.

rembg

Rembg is a tool to remove images background

sahi-yolov8-instance-segmentation

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

Savant

Python Computer Vision & Video Analytics Framework With Batteries Included

starcel-panda3d

TeamTrack

TeamTrack: An Algorithm and Benchmark Dataset for Multi-Sport Multi-Object Tracking in Full-pitch Videos

towhee

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

track-anything-opencv-backend

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

uimadcad

user-friendly graphical environment for madcad

VolleyVision

Applying Deep Learning Approaches to Volleyball Data

VSGAN-tensorrt-docker

Using VapourSynth with super resolution and interpolation models and speeding them up with TensorRT.

yolo_tracking

A collection of SOTA real-time, multi-object tracking algorithms for object detectors