sniklaus/pytorch-pwc
a reimplementation of PWC-Net in PyTorch that matches the official Caffe version
This tool helps researchers and computer vision engineers accurately measure movement between frames in a video or sequence of images. It takes two consecutive image frames and outputs a data file representing the 'optical flow' — essentially, a map of how each pixel moved from the first image to the second. This is useful for tasks like motion analysis, video compression, and object tracking.
654 stars. No commits in the last 6 months.
Use this if you need to precisely calculate the motion vectors between two images and require a robust, well-established optical flow algorithm.
Not ideal if you are looking for real-time performance on embedded systems or if you need a solution for a commercial product without adhering to specific share-alike licensing terms.
Stars
654
Forks
126
Language
Python
License
GPL-3.0
Category
Last pushed
Jan 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sniklaus/pytorch-pwc"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...