FlowSeek
FlowSeek is an optical flow network by Poggi and Tosi (ICCV 2025) that adds a frozen Depth Anything V2 encoder and depth-derived motion bases to a SEA-RAFT style recurrent network. LibreYOLO ports it with four sizes; t and s are Apache-2.0, m and l are for non-commercial use only.
- Tác vụ
- optical flow
- Cài đặt
pip install libreyolo- Bậc hỗ trợ
- Chỉ suy luận, từ v1.8.0. Chỉ dự đoán, kiểm định và xuất. Không áp dụng các tính năng huấn luyện.
- Thượng nguồn
- FlowSeek của University of Bologna, Apache-2.0 (t and s checkpoints); CC-BY-NC-4.0 (m and l checkpoints). Bài báo, mã nguồn
- Giấy phép
- Mã nguồn Apache-2.0, trọng số Apache-2.0 (t and s checkpoints); CC-BY-NC-4.0 (m and l checkpoints). Sử dụng thương mại
FlowSeek borrows geometry knowledge from a depth foundation model:
the Depth Anything V2 encoder features and a set of motion bases computed from
depth feed the recurrent flow update. The hosted checkpoints are upstream's
final generalist fine-tune (TartanAir, Chairs, Things, then a mixed
Sintel, KITTI, HD1K and Things stage), the one upstream evaluates on Spring and
LayeredFlow. Pick t or s for commercial work; m and l carry a
non-commercial encoder.
Install
FlowSeek 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 LibreFlowSeek is also exported from libreyolo if you prefer to build the
model directly.
from libreyolo import LibreYOLO model = LibreYOLO("LibreFlowSeekt-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("LibreFlowSeekt-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=LibreFlowSeekt-flow.pt source=frame_0001.jpg,frame_0002.jpg save=truelibreyolo predict model=LibreFlowSeekt-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. FlowSeek 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
Upstream trains two networks; s and l reuse the t and m
weights with more refinement iterations, as upstream's evaluation configs do.
| Size | Context net | Depth Anything V2 encoder | Iterations | Weights licence |
|---|---|---|---|---|
t | ResNet-18 | ViT-S | 4 | Apache-2.0 |
s | ResNet-18 | ViT-S | 12 | Apache-2.0 |
m | ResNet-34 | ViT-B | 4 | CC BY-NC 4.0, non-commercial |
l | ResNet-34 | ViT-B | 12 | CC BY-NC 4.0, non-commercial |
Files are LibreFlowSeek<size>-flow.pt. LibreFlowSeek defaults to size m,
so pass a t or s checkpoint explicitly if you need commercial-use weights.
Inference runs at native resolution, padded to a multiple of 8 inside the
network, and each side of the padded canvas must be at least 128 px. imgsz
caps the long side.
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("LibreFlowSeekt-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=LibreFlowSeekt-flow.pt data=my_flow.yamlExport
| Tác vụ | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Optical flow | Optical flow to ONNX: không được hỗ trợ | Optical flow to TorchScript: không được hỗ trợ | Optical flow to ExecuTorch: không được hỗ trợ | Optical flow to TensorRT: không được hỗ trợ | Optical flow to OpenVINO: không được hỗ trợ | Optical flow to Paddle: không được hỗ trợ | Optical flow to MNN: không được hỗ trợ | Optical flow to RKNN: không được hỗ trợ | Optical flow to Axelera: không được hỗ trợ | Optical flow to ncnn: không được hỗ trợ | Optical flow to TFLite: không được hỗ trợ | Optical flow to CoreML: không được hỗ trợ | Optical flow to Core AI: không được hỗ trợ |
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.
| Tệp | Giấy phép trọng số |
|---|---|
| Optical flow | |
| LibreFlowSeekt-flow.pt | apache-2.0 |
| LibreFlowSeeks-flow.pt | apache-2.0 |
| LibreFlowSeekm-flow.pt | cc-by-nc-4.0 |
| LibreFlowSeekl-flow.pt | cc-by-nc-4.0 |
Mọi tệp ở trên hiện đều có trong tổ chức LibreYOLO và được tải xuống trong lần sử dụng đầu tiên.
Licensing
Hãy kiểm tra giấy phép trong repo Hugging Face của trọng số cụ thể mà bạn tải xuống. Mỗi checkpoint trong tổ chức LibreYOLO đều có giấy phép riêng và giấy phép có thể khác nhau trong cùng một họ. Repo đó là nguồn có thẩm quyền; phần tóm tắt dưới đây mô tả các điều khoản áp dụng khi trang này được kiểm chứng lần gần nhất.
Đây là phần mô tả các giấy phép liên quan, không phải tư vấn pháp lý. Nếu câu trả lời có ý nghĩa về mặt thương mại, hãy tự đọc các giấy phép và tham khảo cố vấn của riêng bạn.
- Công trình gốc
- FlowSeek, University of Bologna
- Giấy phép thượng nguồn
- Apache-2.0 (t and s checkpoints); CC-BY-NC-4.0 (m and l checkpoints)
- Nguồn thượng nguồn
- github.com/mattpoggi/flowseek
- Mã nguồn LibreYOLO
- MIT
- Trọng số
- Apache-2.0 (t and s checkpoints); CC-BY-NC-4.0 (m and l checkpoints), được phát hành lại tại huggingface.co/LibreYOLO
- Diễn giải
- The two checkpoint licenses are not interchangeable. Each FlowSeek checkpoint embeds a Depth Anything V2 encoder. The t and s checkpoints (one network, s runs 12 refinement iterations instead of 4) embed the ViT-S encoder and are Apache-2.0: they can be used in commercial and closed-source products, with the license text and attribution notices kept on redistribution. The m and l checkpoints embed the ViT-B encoder, which is CC BY-NC 4.0, so they are non-commercial and need attribution; treat them as research weights. Upstream publishes no separate checkpoint license, so the repository's Apache-2.0 license is applied as an implied grant, limited by the encoder license. The code at commit ba640737 is Apache-2.0 with BSD-3-Clause parts from SEA-RAFT, vendored under libreyolo/models/flowseek/_vendor/; LibreYOLO's wrapper code is MIT. Weights come from the upstream get_weights.sh links and are mirrored on the LibreYOLO Hugging Face org, the m and l cards with a non-commercial banner, without gating. Training is out of scope.
FlowSeek is the work of Poggi and Tosi at the University of Bologna. Its code is Apache-2.0 with BSD-3-Clause parts from SEA-RAFT, vendored in LibreYOLO.
The checkpoint licence depends on the size, because each checkpoint embeds a Depth Anything V2 encoder:
tandsembed the ViT-S encoder and are Apache-2.0: commercial and closed-source use is allowed.mandlembed the ViT-B encoder, which is CC BY-NC 4.0: for non-commercial use only, with attribution. Their model cards carry a non-commercial banner and LibreYOLO prints a notice when they load.
Upstream publishes no separate checkpoint licence, so the repository's Apache-2.0 licence is applied as an implied grant, limited by the encoder licence. The weights are mirrored on the LibreYOLO Hugging Face organization without gating.
Citation
@InProceedings{Poggi_2025_ICCV,
author = {Poggi, Matteo and Tosi, Fabio},
title = {FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases},
booktitle = {Proceedings of the International Conference on Computer Vision (ICCV)},
year = {2025},
}Được sao chép từ khối trích dẫn của tác giả tại github.com/mattpoggi/flowseek.