NeuFlow v2

NeuFlow v2 is a high-efficiency optical flow network from the Northeastern University Field Robotics Lab, built for edge devices. It has about 9M parameters and runs on a fixed canvas; it is the edge model among LibreYOLO's flow families.

Zadania
optical flow
Instalacja
pip install libreyolo
Poziom obsługi
Tylko inferencja, od wersji v1.8.0. Tylko predykcja, walidacja i eksport. Funkcje trenowania nie mają zastosowania.
Projekt źródłowy
NeuFlow v2, autorzy: Northeastern University Field Robotics Lab, licencja: Apache-2.0. Publikacja, kod źródłowy
Licencje
Kod: MIT, wagi: Apache-2.0. Użycie komercyjne

NeuFlow v2 pairs a shallow CNN encoder with two cross-attention layers and a global softmax match at 1/16 scale, then a light convolutional refiner at 1/16 and 1/8 scale and a learned 8x convex upsampler. Pick it when speed and memory matter more than the last bit of accuracy, for example on video at frame rate or on small hardware.

Install

NeuFlow v2 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 LibreNeuFlowv2 is also exported from libreyolo if you prefer to build the model directly.

Python
from libreyolo import LibreYOLO model = LibreYOLO("LibreNeuFlowv2s-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("LibreNeuFlowv2s-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=LibreNeuFlowv2s-flow.pt source=frame_0001.jpg,frame_0002.jpg save=truelibreyolo predict model=LibreNeuFlowv2s-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. NeuFlow v2 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 s, with three training-data variants of the same network:

FileUpstream checkpoint
LibreNeuFlowv2s-flow.ptneuflow_mixed.pth, trained on several datasets (canonical)
LibreNeuFlowv2s-flow-sintel.ptneuflow_sintel.pth
LibreNeuFlowv2s-flow-things.ptneuflow_things.pth

Unlike the other flow families, NeuFlow v2 does not run at native resolution. Both frames are stretch-resized to a fixed canvas, 432x768 (height x width) by default as in upstream infer.py; imgsz accepts an int or a (height, width) pair, each side a multiple of 16. The network runs one refinement step at 1/16 and eight at 1/8, and the field is resized back to the original canvas with each vector component multiplied by its axis resize ratio.

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("LibreNeuFlowv2s-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=LibreNeuFlowv2s-flow.pt data=my_flow.yaml

Export

ZadanieONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
Optical flowOptical flow to ONNX: brak obsługiOptical flow to TorchScript: brak obsługiOptical flow to ExecuTorch: brak obsługiOptical flow to TensorRT: brak obsługiOptical flow to OpenVINO: brak obsługiOptical flow to Paddle: brak obsługiOptical flow to MNN: brak obsługiOptical flow to RKNN: brak obsługiOptical flow to Axelera: brak obsługiOptical flow to ncnn: brak obsługiOptical flow to TFLite: brak obsługiOptical flow to CoreML: brak obsługiOptical flow to Core AI: brak obsługi

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.

PlikLicencja wag
Optical flow
LibreNeuFlowv2s-flow.ptapache-2.0
LibreNeuFlowv2s-flow-sintel.ptapache-2.0
LibreNeuFlowv2s-flow-things.ptapache-2.0

Każdy z powyższych plików jest obecnie dostępny w organizacji LibreYOLO i pobierany przy pierwszym użyciu.

Licensing

Sprawdź licencję w repozytorium konkretnych pobieranych wag na Hugging Face. Każdy checkpoint w organizacji LibreYOLO ma licencję, która nie zawsze jest taka sama w całej rodzinie. To repozytorium jest źródłem rozstrzygającym, a poniższe podsumowanie opisuje stan z chwili ostatniej weryfikacji tej strony.

To opis obowiązujących licencji, a nie porada prawna. Jeśli odpowiedź ma znaczenie komercyjne, przeczytaj licencje i zasięgnij własnej porady prawnej.

Oryginalna praca
NeuFlow v2, Northeastern University Field Robotics Lab
Licencja projektu źródłowego
Apache-2.0
Kod LibreYOLO
MIT
Wagi
Apache-2.0, ponownie opublikowane w huggingface.co/LibreYOLO
Interpretacja
Apache-2.0 is a permissive license: the code and weights can be used in commercial and closed-source products. It asks you to keep the license text and attribution notices with redistributed copies, to mark modified files, and it grants a patent license. The upstream model code at commit 204b5e37 is vendored under libreyolo/models/neuflowv2/_vendor/ with its Apache-2.0 LICENSE; LibreYOLO's wrapper code is MIT. Upstream commits its three checkpoints (neuflow_mixed.pth as the canonical s, neuflow_sintel.pth and neuflow_things.pth as variants) to the Apache-2.0 repository with no separate weight license, so LibreYOLO mirrors them on its Hugging Face org under Apache-2.0, an implied grant from the releasing project. No gating; inference only.

NeuFlow v2 is the work of the Northeastern University Field Robotics Lab. The upstream model code is vendored under its Apache-2.0 licence. Upstream commits its three checkpoints to the same Apache-2.0 repository with no separate weight licence, so LibreYOLO mirrors them under Apache-2.0, without gating. Apache-2.0 allows commercial and closed-source use; keep the licence text and attribution notices on redistribution.

Citation

@misc{zhang2025neuflowv2pushhighefficiency,
      title={NeuFlow v2: Push High-Efficiency Optical Flow To the Limit}, 
      author={Zhiyong Zhang and Aniket Gupta and Huaizu Jiang and Hanumant Singh},
      year={2025},
      eprint={2408.10161},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2408.10161}, 
}

Skopiowano z bloku cytowania autorów w arxiv.org/abs/2408.10161.

Zweryfikowano z LibreYOLO v1.8.0. Tabele obsługi, checkpointy i wyniki benchmarków na tej stronie są generowane na podstawie wydanej biblioteki i opublikowanych wag, a nie wpisywane ręcznie.