# lmb-freiburg/flownet2

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Repository: https://github.com/lmb-freiburg/flownet2
Canonical: https://ross.abutalabs.com/products/flownet2
Homepage: https://lmb.informatik.uni-freiburg.de/Publications/2017/IMKDB17/
Language: C++
License: NOASSERTION
License Family: other
Topics: caffe, cnn, optical-flow, cvpr
Last push: 2019-07-30T07:20:10+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3417, "days_push": 2591, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1024, forks 317 (observed 2026-08-28T04:03:16.335819+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: cpp, python
- tags: optical-flow, caffe, cnn, cvpr-2017, research-code, linux

## Member repositories
- lmb-freiburg/flownet2 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:16.335819+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:08:14.237974+00:00, confidence not recorded.
  - readme: https://github.com/lmb-freiburg/flownet2 (fetched 2026-08-28T04:03:16.335819+00:00, sha cb9c6e2d0596)
  - homepage: https://lmb.informatik.uni-freiburg.de/Publications/2017/IMKDB17/ (fetched 2026-08-29T13:08:28.267620+00:00, sha 908c149d2453)
- Data as of 2026-08-30T08:39:29.467469+00:00.