WAFT

WAFT, Warping-Alone Field Transforms, is an optical flow method by Wang and Deng (ICLR 2026). It replaces RAFT's cost volume with high-resolution feature warping and a ViT refinement loop. LibreYOLO ports the upstream code and mirrors its four zero-shot checkpoints, one per feature encoder.

Tâches
optical flow
Installer
pip install libreyolo
Niveau de support
Inférence uniquement, depuis v1.8.0. Prédiction, validation et export uniquement. Les fonctionnalités d'entraînement ne s'appliquent pas.
Origine
WAFT par Princeton Vision & Learning Lab, BSD-3-Clause (s, m and l checkpoints); DINOv3 License (t checkpoint). Article, source
Licences
Code BSD-3-Clause, poids BSD-3-Clause (s, m and l checkpoints); DINOv3 License (t checkpoint). Usage commercial

WAFT drops the correlation volume that RAFT and its descendants build, and instead warps high-resolution features of the second frame with the current flow estimate before each refinement step. All four checkpoints are upstream's zero-shot models (TartanAir, then Chairs, then Things). Pick m, the a1 checkpoint the upstream README recommends for downstream use, unless you have a reason to choose a specific encoder.

Install

WAFT 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 LibreWAFT is also exported from libreyolo if you prefer to build the model directly.

Python
from libreyolo import LibreYOLO model = LibreYOLO("LibreWAFTm-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("LibreWAFTm-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=LibreWAFTm-flow.pt source=frame_0001.jpg,frame_0002.jpg save=truelibreyolo predict model=LibreWAFTm-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. WAFT 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

SizeUpstream checkpointParametersFile
ta2, DINOv3 ViT-S/16 encoder56.5 MLibreWAFTt-flow-dinov3.pt
sa2, Depth Anything V2 ViT-S56.9 MLibreWAFTs-flow-dav2.pt
ma1, Depth Anything V2 ViT-S64.2 MLibreWAFTm-flow.pt
la2, Twins-SVT-Large encoder136.0 MLibreWAFTl-flow-twins.pt

The encoder is the weight variant in the file name, and each size exists only under the name in the table; any other combination raises with the published name. LibreWAFT defaults to size m. Prediction runs at native resolution: the network pads the pair to a multiple of 112, 32 or 16 depending on the encoder and crops the flow back. Five refinement iterations are baked in, the upstream evaluation default. imgsz caps the long side (default 8192, in practice no cap).

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

Export

TâcheONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
Optical flowOptical flow to ONNX : non pris en chargeOptical flow to TorchScript : non pris en chargeOptical flow to ExecuTorch : non pris en chargeOptical flow to TensorRT : non pris en chargeOptical flow to OpenVINO : non pris en chargeOptical flow to Paddle : non pris en chargeOptical flow to MNN : non pris en chargeOptical flow to RKNN : non pris en chargeOptical flow to Axelera : non pris en chargeOptical flow to ncnn : non pris en chargeOptical flow to TFLite : non pris en chargeOptical flow to CoreML : non pris en chargeOptical flow to Core AI : non pris en charge

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.

FichierLicence des poids
Optical flow
LibreWAFTm-flow.ptbsd-3-clause
LibreWAFTt-flow-dinov3.ptDINOv3 License
LibreWAFTs-flow-dav2.ptbsd-3-clause
LibreWAFTl-flow-twins.ptbsd-3-clause

Tous les fichiers ci-dessus sont actuellement disponibles dans l<link>organisation LibreYOLO</link> et sont téléchargés à la première utilisation.

Licensing

Vérifiez la licence dans le dépôt Hugging Face des poids précis que vous téléchargez. Chaque checkpoint de l<link>organisation LibreYOLO</link> en possède une, et elles ne sont pas toujours identiques au sein dune même famille. Ce dépôt fait autorité ; le résumé ci-dessous décrit les conditions applicables lors de la dernière vérification de cette page.

Ceci décrit les licences concernées et ne constitue pas un conseil juridique. Si la réponse a une importance commerciale, lisez vous-même les licences et consultez votre propre avocat.

Travail d'origine
WAFT, Princeton Vision & Learning Lab
Licence du projet d'origine
BSD-3-Clause (s, m and l checkpoints); DINOv3 License (t checkpoint)
Source du projet d'origine
github.com/princeton-vl/WAFT
Code de LibreYOLO
MIT
Poids
BSD-3-Clause (s, m and l checkpoints); DINOv3 License (t checkpoint), republiés sur huggingface.co/LibreYOLO
Interprétation
The license depends on the size, because each checkpoint embeds a different encoder. The s, m and l checkpoints are BSD-3-Clause, a permissive license that allows commercial and closed-source use as long as the copyright notice, conditions and disclaimer are kept on redistribution; their encoders are Apache-2.0 (Depth Anything V2 Small for s and m, Twins-SVT-Large from timm for l), which is also permissive. The t checkpoint contains a DINOv3 ViT-S/16 fine-tuned by the WAFT authors, so Meta's DINOv3 License applies to it: a custom license, not OSI-approved, with its own use restrictions and conditions; read it before relying on t commercially. Upstream publishes no separate weight license, so LibreYOLO hosts the checkpoints under the repository's BSD-3-Clause license plus the encoder license. The code from princeton-vl/WAFT at commit b152ff1 is vendored under libreyolo/models/waft/_vendor/ (BSD-3-Clause); the encoders reuse code already in LibreYOLO (Depth Anything V2, Apache-2.0; DINOv3 from the DEIMv2 vendor, DINOv3 License) and a plain-torch Twins copy derived from timm (Apache-2.0). LibreYOLO's wrapper code is MIT. Weights come from the upstream Google Drive model zoo and are mirrored on the LibreYOLO Hugging Face org without gating. Inference only.

WAFT is the work of Wang and Deng at the Princeton Vision & Learning Lab. The upstream code is vendored under its BSD-3-Clause licence. Upstream publishes no separate weight licence, so LibreYOLO mirrors the checkpoints under the repository's BSD-3-Clause licence plus the licence of the encoder each one embeds, without gating.

  • s, m and l are BSD-3-Clause. Their encoders are Apache-2.0 (Depth Anything V2 Small for s and m, a Twins-SVT-Large copy derived from timm for l). Commercial and closed-source use is allowed.
  • t contains a DINOv3 ViT-S/16 fine-tuned by the WAFT authors, so Meta's DINOv3 License applies to it: a custom licence, not OSI-approved, with its own use restrictions and trade-control terms. Read it before using t commercially.

Citation

@article{wang2025waft,
  title={WAFT: Warping-Alone Field Transforms for Optical Flow},
  author={Wang, Yihan and Deng, Jia},
  journal={arXiv preprint arXiv:2506.21526},
  year={2025}
}

Copié depuis le bloc de citation des auteurs sur github.com/princeton-vl/WAFT.

Vérifié avec LibreYOLO v1.8.0. Les tableaux de support, les checkpoints et les chiffres de benchmark de cette page sont générés à partir de la bibliothèque publiée et des poids publiés, et non rédigés à la main.