anuragranj/spynet
Spatial Pyramid Network for Optical Flow
This project helps computer vision practitioners analyze motion between consecutive video frames or image sequences. It takes in two images and calculates the 'optical flow', which describes how each pixel in the first image moves to its new position in the second image. The output is a flow field that can be used for motion analysis, video compression, or action recognition.
252 stars. No commits in the last 6 months.
Use this if you need to precisely quantify and visualize motion between two images, such as tracking objects or analyzing scene dynamics.
Not ideal if you are looking for a plug-and-play solution in Python or TensorFlow, as this implementation specifically uses Torch/Lua.
Stars
252
Forks
48
Language
Lua
License
—
Category
Last pushed
Sep 23, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/anuragranj/spynet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
patrick-llgc/Learning-Deep-Learning
Paper reading notes on Deep Learning and Machine Learning
magicleap/SuperGluePretrainedNetwork
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
eric-yyjau/pytorch-superpoint
Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629
lucasb-eyer/pydensecrf
Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials.
changhao-chen/deep-learning-localization-mapping
A collection of deep learning based localization models