DPFlow

DPFlow is an adaptive optical flow estimator by Henrique Morimitsu and co-authors (CVPR 2025). Its dual-pyramid encoder adapts its depth to the input size, so a model trained at low resolution generalises to 4K and 8K frames. LibreYOLO ports it from ptlflow; the weights are licensed CC BY-NC-SA 4.0, for non-commercial use only.

Задачи
optical flow
Установка
pip install libreyolo
Уровень поддержки
Только инференс, начиная с v1.8.0. Только предсказание, валидация и экспорт. Функции обучения неприменимы.
Исходный проект
DPFlow от Henrique Morimitsu (ptlflow), CC-BY-NC-SA-4.0. Статья, исходный код
Лицензии
Код: Apache-2.0, веса: CC-BY-NC-SA-4.0. Коммерческое использование

DPFlow chooses the number of pyramid levels from the image diagonal: three levels around 1K, one more per doubling. LibreYOLO keeps that rule and runs at the native frame resolution by default, which is where the adaptive depth matters. Pick it for research on high-resolution footage; its weights are non-commercial.

Install

DPFlow needs no optional extra. Everything it imports is in the base install.

bash
pip install libreyolo

Predict

Weights download from the LibreYOLO Hugging Face organization on first use. The class LibreDPFlow is also exported from libreyolo if you prefer to build the model directly.

Python
from libreyolo import LibreYOLO model = LibreYOLO("LibreDPFlowm-flow.pt")   # weights download on first useresults = model(["frame_0001.jpg", "frame_0002.jpg"]) flow = results[0].flowprint(flow.data.shape)        # (H, W, 2) float32, (dx, dy) in pixelsprint(flow.mean_magnitude)    # mean displacement in pixels
Video
from libreyolo import LibreYOLO model = LibreYOLO("LibreDPFlowm-flow.pt") # N frames give N - 1 results; result i is the flow from frame i to i + 1.for result in model("video.mp4", stream=True, save=True, save_flow=True):    print(result.flow.max_magnitude)
CLI
libreyolo predict model=LibreDPFlowm-flow.pt source=frame_0001.jpg,frame_0002.jpg save=truelibreyolo predict model=LibreDPFlowm-flow.pt source=video.mp4 save=true arrows=true save_flow=true

Flow needs at least two frames: a single image raises. A list of images, a directory sorted by name, a video or a stream is one sequence, and N frames give N - 1 results. result.flow is a FlowField with an (H, W, 2) float32 array on the original canvas of the first frame; flow.data[y, x] is (dx, dy) in pixels, +x right and +y down. DPFlow fills no confidence map, so flow.confidence is None. result.boxes is None. save=True writes the Middlebury colour wheel, arrows=True or warp=True pick the other views, and save_flow=True also writes each pair's raw field as a .flo file. The optical flow task page describes the payload and views in full.

Variants

One architecture, size m, with four checkpoints:

FileTraining stage
LibreDPFlowm-flow.ptFlyingThings3D (things), the generalisation checkpoint (canonical)
LibreDPFlowm-flow-sintel.ptSintel fine-tune
LibreDPFlowm-flow-kitti.ptKITTI fine-tune
LibreDPFlowm-flow-spring.ptSpring fine-tune

The iteration schedule is fixed at upstream's test setting, 4 refinement iterations per pyramid level. Every pair is estimated independently: the upstream warm start across frames is not used. imgsz caps the long side (default 8192, in practice no cap); frames above it are downscaled and the field is scaled back to the original canvas.

Training is not offered: train() raises NotImplementedError.

Validate

val() runs the shared flow validator on a flow dataset (frames per sequence folder, Middlebury .flo, KITTI 16-bit PNG or .npy ground truth; see the dataset format). It reports the mean end-point error metrics/epe, metrics/px1 and metrics/px3 (share of valid pixels under 1 and 3 px of error) and the KITTI outlier rate metrics/fl_all.

Python
from libreyolo import LibreYOLO model = LibreYOLO("LibreDPFlowm-flow.pt")metrics = model.val(data="my_flow.yaml") print(metrics["metrics/epe"])      # mean end-point error, pixelsprint(metrics["metrics/px1"])      # share of pixels under 1 px errorprint(metrics["metrics/fl_all"])   # KITTI outlier rate
CLI
libreyolo val model=LibreDPFlowm-flow.pt data=my_flow.yaml

Export

ЗадачаONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
Optical flowOptical flow to ONNX: не поддерживаетсяOptical flow to TorchScript: не поддерживаетсяOptical flow to ExecuTorch: не поддерживаетсяOptical flow to TensorRT: не поддерживаетсяOptical flow to OpenVINO: не поддерживаетсяOptical flow to Paddle: не поддерживаетсяOptical flow to MNN: не поддерживаетсяOptical flow to RKNN: не поддерживаетсяOptical flow to Axelera: не поддерживаетсяOptical flow to ncnn: не поддерживаетсяOptical flow to TFLite: не поддерживаетсяOptical flow to CoreML: не поддерживаетсяOptical flow to Core AI: не поддерживается

Export is not available yet for any format. Optical flow export is blocked until the two-input graph (image1, image2) and the backend vector-rescale contract of the flow task are implemented for a family.

Checkpoints

Every published weight file for this family.

ФайлЛицензия весов
Optical flow
LibreDPFlowm-flow.ptcc-by-nc-sa-4.0
LibreDPFlowm-flow-sintel.ptcc-by-nc-sa-4.0
LibreDPFlowm-flow-kitti.ptcc-by-nc-sa-4.0
LibreDPFlowm-flow-spring.ptcc-by-nc-sa-4.0

Все перечисленные выше файлы уже доступны в организации LibreYOLO и скачиваются при первом использовании.

Licensing

Проверяйте лицензию в репозитории конкретных весов на Hugging Face. Она указана для каждого чекпойнта в организации LibreYOLO и может различаться даже внутри одного семейства. Этот репозиторий считается авторитетным источником, а сводка ниже описывает условия на момент последней проверки страницы.

Это описание соответствующих лицензий, а не юридическая консультация. Если ответ важен для коммерческого использования, прочитайте лицензии самостоятельно и проконсультируйтесь с юристом.

Оригинальная работа
DPFlow, Henrique Morimitsu (ptlflow)
Лицензия исходного проекта
CC-BY-NC-SA-4.0
Исходный код проекта
github.com/hmorimitsu/ptlflow
Код LibreYOLO
MIT
Веса
CC-BY-NC-SA-4.0, повторно опубликованы на huggingface.co/LibreYOLO
Толкование
The code and the weights carry different licenses. The weights were trained within ptlflow and are released under CC BY-NC-SA 4.0: commercial use is not allowed, redistribution needs attribution, and anything you build from the weights and share must carry the same license; the DPFlow README adds that the weights are for academic and research purposes only, because of the training datasets' licenses. Treat all four checkpoints (things as the canonical m, and the sintel, kitti and spring fine-tunes) as research weights. The code is Apache-2.0: ptlflow's models/dpflow at commit 43cdc2b5 is vendored under libreyolo/models/dpflow/_vendor/, with timm-derived helpers (Apache-2.0) and an input padder adapted from RAFT (BSD-3-Clause); LibreYOLO's wrapper code is MIT. The weights come from the ptlflow weights1 release and are mirrored on the LibreYOLO Hugging Face org with the license text and a non-commercial banner, without gating. Training is out of scope.

DPFlow is the work of Henrique Morimitsu and co-authors, released in ptlflow. The code and the weights carry different licences.

  • The code is Apache-2.0: ptlflow's models/dpflow is vendored with timm-derived helpers (Apache-2.0) and an input padder adapted from RAFT (BSD-3-Clause).
  • The weights are CC BY-NC-SA 4.0: non-commercial use only, attribution required, and anything you build from them and share must carry the same licence. The DPFlow README adds that the weights are for academic and research purposes only, because of the training datasets' licences. Treat all four checkpoints as research weights.

LibreYOLO mirrors the weights with the licence text and a non-commercial banner, without gating, and prints a notice when they load.

Citation

@InProceedings{Morimitsu2025DPFlow,
  author    = {Morimitsu, Henrique and Zhu, Xiaobin and Cesar-Jr., Roberto M. and Ji, Xiangyang and Yin, Xu-Cheng},
  booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title     = {{DPFlow}: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework},
  year      = {2025},
}

Скопировано из блока цитирования авторов на странице github.com/hmorimitsu/ptlflow/tree/43cdc2b5fc7228e7090009a66e8e28e0b48e31ba/ptlflow/models/dpflow#citation.

Проверено с LibreYOLO v1.8.0. Таблицы поддержки, чекпойнты и результаты бенчмарков на этой странице сгенерированы из выпущенной библиотеки и опубликованных весов, а не написаны вручную.