jsxapril

omniglue

Code release for CVPR'24 submission 'OmniGlue'

UniDetector

Code release for our CVPR 2023 paper "Detecting Everything in the Open World: Towards Universal Object Detection".

Two-stage-Knowledge-For-Multiple-Adverse-Weather-Removal

[CVPR 2022] Learning Multiple Adverse Weather Removal via Two-stage Knowledge Learning and Multi-contrastive Regularization: Toward a Unified Model

WeatherStream

Official Github repository for WeatherStream: Light Transport Automation of Single Image Deweathering, CVPR 2023

tapnet

Tracking Any Point (TAP)

RAFT

mmflow

OpenMMLab optical flow toolbox and benchmark

CONTRIQUE

Official implementation for "Image Quality Assessment using Contrastive Learning"

PIQ2023

Noise-Level-Estimation

Single-Image Noise Level Estimation for Blind Denoising

noise_est_ICCV2015

An Efficient Statistical Method for Image Noise Level Estimation, ICCV 2015, Python

blind_image_quality_toolbox

Collection of Blind Image Quality Metrics in Matlab

piq

Measures and metrics for image2image tasks. PyTorch.

DISTS

IQA: Deep Image Structure and Texture Similarity Metric

hyperIQA

Source code for the CVPR'20 paper "Blindly Assess Image Quality in the Wild Guided by A Self-Adaptive Hyper Network"

LightGlue-ONNX

ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO

LightGlue-OpenCV

LightGlue-OpenCV

LightGlue

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

image-quality-tools

image-quality-assessment-toolbox

Some commonly-used image quality assessment algorithms.

Grid-Anchor-based-Image-Cropping-Pytorch

PyTorch implementation of "Grid anchor based image cropping"

FRIQA-ActMapFeat

Full-reference image quality assessment based on convolutional activation maps.

VideoFlow

Official implementation of ICCV2023 VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation

flowsam

Official Implementation of "Moving Object Segmentation: All You Need Is SAM (and Flow)" Junyu Xie, Charig Yang, Weidi Xie, Andrew Zisserman

OpticalFlow-LucasKanade-Farneback-Detection-Tracking

implement LucasKanade optical flow and Farneback optical flow, and implement pedestrian detection demo and target tracking demo based on these two methods

Auto-cam-movement-detection

Detecting the movement of the camera automatically is not a simple task for obvious reasons. Here, I have made an attempt to detect the movement of the camera either external or inbuilt using the concept of optical flow.

OpticalFlow-movingTargetDetection

BB-SGD

Original implementation of the background reconstruction model described in the paper "Fast and accurate background reconstruction using background bootstrapping"

illumination_augmentation

Illumination-Based Data Augmentation for Robust Background Subtraction, SKIMA 2019. Best paper award.

Eigenbackground-Revisited

MATLAB code for Eigenbackground-Revisited paper