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.
- Tasks
- optical flow
- Install
pip install libreyolo- Support tier
- Inference only, since v1.8.0. Predict, validate and export only. Training features do not apply.
- Licenses
- Code MIT, weights Apache-2.0. Commercial use
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.
pip install libreyoloPredict
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.
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 pixelsfrom 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)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=trueFlow 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:
| File | Upstream checkpoint |
|---|---|
LibreNeuFlowv2s-flow.pt | neuflow_mixed.pth, trained on several datasets (canonical) |
LibreNeuFlowv2s-flow-sintel.pt | neuflow_sintel.pth |
LibreNeuFlowv2s-flow-things.pt | neuflow_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.
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 ratelibreyolo val model=LibreNeuFlowv2s-flow.pt data=my_flow.yamlExport
| Task | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Optical flow | Optical flow to ONNX: not supported | Optical flow to TorchScript: not supported | Optical flow to ExecuTorch: not supported | Optical flow to TensorRT: not supported | Optical flow to OpenVINO: not supported | Optical flow to Paddle: not supported | Optical flow to MNN: not supported | Optical flow to RKNN: not supported | Optical flow to Axelera: not supported | Optical flow to ncnn: not supported | Optical flow to TFLite: not supported | Optical flow to CoreML: not supported | Optical flow to Core AI: not supported |
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.
| File | Weights license |
|---|---|
| Optical flow | |
| LibreNeuFlowv2s-flow.pt | apache-2.0 |
| LibreNeuFlowv2s-flow-sintel.pt | apache-2.0 |
| LibreNeuFlowv2s-flow-things.pt | apache-2.0 |
Every file above exists in the LibreYOLO org today and downloads on first use.
Licensing
Check the license on the Hugging Face repository of the specific weights you download. Every checkpoint in the LibreYOLO org carries one, and they are not always the same across a family. That repository is the authoritative source; the summary below describes what applied when this page was last verified.
This is a description of the licenses involved, not legal advice. If the answer matters commercially, read the licenses yourself and take your own counsel.
- Original work
- NeuFlow v2, Northeastern University Field Robotics Lab
- Upstream license
- Apache-2.0
- Upstream source
- github.com/neufieldrobotics/NeuFlow_v2
- LibreYOLO code
- MIT
- Weights
- Apache-2.0, republished at huggingface.co/LibreYOLO
- Interpretation
- 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},
}Copied from the authors' citation block at arxiv.org/abs/2408.10161.