# NVlabs/PWC-Net

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)

Repository: https://github.com/NVlabs/PWC-Net
Canonical: https://ross.abutalabs.com/products/pwc-net
Language: Python
License: NOASSERTION
License Family: other
Topics: deeplearning, optical-flow, computer-vision, pytorch, caffe, cvpr2018, pwc-net
Last push: 2022-08-22T16:53:14+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": 3003, "days_push": 1472, "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 1736, forks 365 (observed 2026-08-28T04:05:29.740279+00:00)

## What it is
Official NVIDIA implementation of PWC-Net, a CNN for optical flow estimation using pyramid, warping, and cost volume, released with CVPR 2018. Provides Caffe and PyTorch implementations with pretrained models.

## Use cases
- estimate optical flow between video frames
- compute dense motion fields for video analysis
- run pretrained optical flow model in pytorch
- reproduce CVPR 2018 optical flow results
- motion estimation for video stabilization

## When to choose
- you need a well-known baseline optical flow model
- you want Caffe or PyTorch pretrained optical flow networks

## When to avoid
- you need a permissive commercial license (CC BY-NC-SA only)
- you need actively maintained code or modern framework support

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning
- domain: computer-vision, deep-learning
- platform: python
- tags: optical-flow, pytorch, caffe, research-code, non-commercial-license, linux

## Member repositories
- NVlabs/PWC-Net (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:29.740279+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 2026-08-30T03:30:40.129992+00:00, confidence not recorded.
  - readme: https://github.com/NVlabs/PWC-Net (fetched 2026-08-28T04:05:29.740279+00:00, sha 0f95ee4ec546)
- Data as of 2026-08-30T08:39:29.467469+00:00.