lmb-freiburg/flownet2

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1024 stars · 317 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Caffe fork implementing FlowNet 2.0, a deep CNN for optical flow estimation from image pairs, released with the CVPR 2017 paper. It includes trained models, scripts for running inference on single or many image pairs, and training pipelines.

Use cases

• estimate optical flow between two images with a deep network
• compute flow fields for video frames at interactive frame rates
• retrain FlowNet2 on custom optical flow datasets
• reproduce CVPR 2017 optical flow research results
• batch-process many image pairs to .flo flow files

When to choose

• you need the original FlowNet2 models and training setup for research reproduction
• your stack is already Caffe-based and runs on Linux with GPU
• you want a proven optical flow baseline for comparison

When to avoid

• you want a modern PyTorch or TensorFlow implementation
• you need commercial use - the license forbids it without consent
• you need active maintenance or easy installation on recent systems

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning cpp python optical-flow caffe cnn cvpr-2017 research-code linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lmb-freiburg/flownet2")