| --- |
| license: cc-by-nc-sa-4.0 |
| pipeline_tag: image-to-image |
| library_name: libreyolo |
| tags: |
| - optical-flow |
| - dpflow |
| - libreflow |
| - libreyolo |
| --- |
| |
| # LibreDPFlowm-flow |
|
|
| > **Non-commercial weights.** These DPFlow weights are licensed |
| > **CC BY-NC-SA 4.0** by their author (trained within ptlflow). They are for |
| > non-commercial use only and are **not** covered by LibreYOLO's MIT license. |
| > You are responsible for complying with the weight license. |
|
|
| DPFlow (CVPR 2025) optical flow, repackaged for LibreYOLO's `flow` task. This |
| checkpoint is the `things` stage: FlyingChairs then FlyingThings3D (the standard generalisation checkpoint; LibreYOLO's default). |
|
|
| DPFlow's dual-pyramid encoder picks its depth from the image diagonal (three |
| levels around 1K, one more per doubling), so it runs at the native resolution |
| of the frames and generalises to 4K and 8K inputs. LibreYOLO keeps that rule |
| and the upstream test schedule (4 refinement iterations per level). |
|
|
| ## Usage |
|
|
| ```python |
| from libreyolo import LibreYOLO |
| |
| model = LibreYOLO("LibreDPFlowm-flow.pt") # auto-downloads from this repo |
| r = model(["frame_000.png", "frame_001.png"])[0] |
| r.flow.data # (H, W, 2) float32, pixels, (dx, dy) from frame 0 to frame 1 |
| r.flow.to_rgb() # Middlebury colour wheel |
| ``` |
|
|
| ## Source |
|
|
| Derived from [hmorimitsu/ptlflow](https://github.com/hmorimitsu/ptlflow) |
| (`ptlflow/models/dpflow`, code at commit `43cdc2b5fc7228e7090009a66e8e28e0b48e31ba`), weight file `dpflow-things-2012b5d6.ckpt` from |
| the [weights1 release](https://github.com/hmorimitsu/ptlflow/releases/tag/weights1). |
| Copyright 2025 Henrique Morimitsu. |
|
|
| Morimitsu, H., Zhu, X., Cesar Jr, R. M., Ji, X., and Yin, X.-C. "DPFlow: |
| Adaptive Optical Flow Estimation with a Dual-Pyramid Framework." CVPR 2025. |
|
|
| ## Modifications |
|
|
| State-dict metadata wrapping only. Learned parameters are unchanged. |
| See `weights/convert_dpflow_weights.py` in the |
| [LibreYOLO source repository](https://github.com/LibreYOLO/libreyolo). |
|
|
| ## Parity |
|
|
| Checked on an RTX 3090 against ptlflow's own `DPFlow` (commit `43cdc2b5`) on 23 consecutive 640x360 frame pairs, fp32, TF32 off, deterministic cuDNN: max absolute difference 0.0 px, mean 0.0 px (bitwise identical). Upstream-reported validation for this checkpoint (ptlflow README): Sintel clean EPE 1.02, Sintel final EPE 2.27, KITTI 2015 EPE 3.39. |
|
|
| ## License |
|
|
| Weights: CC BY-NC-SA 4.0. See the [`LICENSE`](./LICENSE) and |
| [`NOTICE`](./NOTICE) files in this repository. The DPFlow code is Apache-2.0. |
|
|
