Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
PhyCV: The First Physics-inspired Computer Vision Library
| Date | Stars |
|---|---|
| 2026-07-31 | 527 |
| 2026-08-04 | 527 |
| 2026-08-06 | 527 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center"> <img src="assets/misc/phycv_logo.png"> </p> # PhyCV: The First Physics-inspired Computer Vision Library <a href="https://colab.research.google.com/drive/1_4OASJRSkwc6u1kq8mqMNfqpo3h_0pGU?usp=sharing"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="google colab logo"></a> [](https://pypi.org/project/phycv/) [](https://arxiv.org/abs/2301.12531) [](https://www.youtube.com/playlist?list=PLj--iTBXPaTWABQstUFA6l6_Rf3uiZq9T) [](https://en.wikipedia.org/wiki/PhyCV) Welcome to PhyCV ! The First Physics-inspired Computer Vision Python library developed by [Jalali-Lab](https://photonics.ucla.edu/) @ UCLA. This repo is maintained by [Yiming Zhou](https://yiming0416.github.io/). See the release notes [here](./assets/docs/change_log.md). We released the C++ version of PhyCV with CUDA acceleration. Check out the PhyCV-CUDA repo [here](https://github.com/JalaliLabUCLA/phycv-cuda)! ## Contents * [Introduction](#introduction) * [Folder Structure](#folder-structure) * [Installation](#installation) * [Phase-Stretch Transform (PST)](#phase-stretch-transform-pst) * [Phase-Stretch Adaptive Gradient-field Extractor (PAGE)](#phase-stretch-adaptive-gradient-field-extractor-page) * [Vision Enhancement via Virtual diffraction and coherent Detection (VEViD)](#vision-enhancement-via-virtual-diffraction-and-coherent-detection-vevid) * [Sample Results](#sample-results) * [Reference](#reference) * [Citation](#citation) ## Introduction PhyCV is a Physics-inspired Computer Vision Python library. PhyCV has a new class of computer vision algorithms that emulates the propagation of light through a physical medium with natural and engineered diffractive properties followed by coherent detection. Unlike traditional algorithms that are a sequence of hand-crafted empirical rules, physics-inspired algorithms leverage physical laws of nature as blueprints. These algorithms can, in principle, be implemented in real physical devices for fast and efficient computation. Currently, PhyCV includes Phase-Stretch Transform (PST), Phase-Stretch Adaptive Gradient-field Extractor (PAGE) and Vision Enhancement via Virtual diffraction and coherent Detection (VEViD). Each algorthm has CPU and GPU versions. ## Folder Structure - `assets`: sample input images/videos, sample results, documentations. - `phycv`: source code of PhyCV. - `scripts`: examples of running PhyCV with python scripts. ## Installation The GPU versions depend on `PyTorch` and `torchvision`. Please follow the instructions on [PyTorch Official Website](https://pytorch.org/) to install the correct version of `CUDA ToolKit` and `PyTorch` according to your system setup. **From pip** ```bash pip install phycv ``` **From source** ```bash git clone https://github.com/JalaliLabUCLA/phycv.git cd phycv pip install . ``` ## Phase-Stretch Transform (PST) Phase Stretch Transform (PST) is a computationally efficient edge and texture detection algorithm with exceptional performance in visually impaired images. Inspired by the physics of the photonic time stretch [1], [2] (an ultrafast and single-shot data acquisition technique), the algorithm transforms the image by emulating propagation of light through a device with engineered dispersive/diffractive property followed by coherent detection [3], [4], [5], [[wiki]](https://en.wikipedia.org/wiki/Phase_stretch_transform). It has been successfully used in many applications [6], [7], [8]. See more docs [here](./assets/docs/pst.md). ## Phase-Stretch Adaptive Gradient-field Extractor (PAGE) Phase-Stretch Adaptive Gradient-field Extractor (PAGE) is a physics-inspired algorithm for dete
Excerpt of 10,784 characters
Read on GitHub
59
12
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:68f19f7c97154828, desc:computer vision