NVlabs/pacnet
Pixel-Adaptive Convolutional Neural Networks (CVPR '19)
This project provides advanced image processing components that can enhance the quality of various computer vision tasks. It takes an input image and a 'guidance' image to produce a refined output image or feature map. Researchers and engineers working on image enhancement, semantic segmentation, or other pixel-level prediction problems would use this to improve model performance.
518 stars. No commits in the last 6 months.
Use this if you are developing computer vision models and need to integrate context-aware, adaptive filtering to improve the accuracy of pixel-level predictions, such as refining image details or segmentation boundaries.
Not ideal if you are looking for a complete, out-of-the-box solution for a specific image processing task, rather than a set of fundamental building blocks for neural networks.
Stars
518
Forks
78
Language
Python
License
—
Category
Last pushed
Dec 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVlabs/pacnet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.