Video Depth Anything

Video Depth Anything, by ByteDance, puts a temporal head on the Depth Anything V2 encoder so depth stays consistent from frame to frame. LibreYOLO runs a list of frames, a folder, a video or a stream as one sequence and returns one depth map per frame, all on one relative scale.

Tâches
depth
Tailles
s, b, l at 518 px
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
Video Depth Anything par ByteDance, Apache-2.0 (Small checkpoint); CC-BY-NC-4.0 (Base and Large checkpoints). Article, source
Licences
Code Apache-2.0, poids Apache-2.0 (s); CC-BY-NC-4.0 (b, l). Usage commercial

Install

Video Depth Anything needs no optional extra.

bash
pip install libreyolo

Predict

Weights download from the LibreYOLO Hugging Face mirrors on first use.

Video
from libreyolo import LibreYOLO model = LibreYOLO("LibreVideoDepthAnythings-depth.pt") # One result per frame, streamed with at most one window of lag.for result in model("clip.mp4", stream=True):    depth = result.depth_map.data      # (H, W) relative inverse depth
One image
from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreVideoDepthAnythings-depth.pt")result = model(SAMPLE_IMAGE, save=True)   # a one-frame sequenceprint(result.depth_map.data.shape)
CLI
libreyolo predict model=LibreVideoDepthAnythings-depth.pt source=clip.mp4 save=True

Any multi-image source is one sequence: a list of frames, a directory sorted by name, a video file or a stream. N frames give N results, each with a result.depth_map on that frame's canvas. Inside, frames run in upstream's overlapping 32-frame windows, and each window is scale and shift aligned to the ones before it, so the whole sequence shares one relative scale. A single image is a one-frame sequence; upstream pads it to a full window with copies of itself.

The output follows LibreYOLO's shared depth contract: relative inverse depth, where higher values are closer and the values have no metric unit. The input size is upstream's default of 518 for every encoder; frames wider than 16:9 run proportionally smaller, as upstream does. See the depth estimation task page for the payload.

Variants

Three encoder sizes, s, b and l, one checkpoint each. The licence differs by size (see below), so s is the one to use in a commercial product. Upstream's metric-depth checkpoints are not hosted, and the converter refuses them.

Training is not offered: train() raises. Convert an upstream relative-depth checkpoint with weights/convert_video_depth_anything_weights.py in the library.

Export

TâcheONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
DepthDepth to ONNX : non pris en chargeDepth to TorchScript : non pris en chargeDepth to ExecuTorch : non pris en chargeDepth to TensorRT : non pris en chargeDepth to OpenVINO : non pris en chargeDepth to Paddle : non pris en chargeDepth to MNN : non pris en chargeDepth to RKNN : non pris en chargeDepth to Axelera : non pris en chargeDepth to ncnn : non pris en chargeDepth to TFLite : non pris en chargeDepth to CoreML : non pris en chargeDepth to Core AI : non pris en charge

Export is not supported. The network reads a 32-frame window and the windows are stitched on the host, which the single-image depth export contract does not describe, so export() raises.

Checkpoints

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
Video Depth Anything, ByteDance
Licence du projet d'origine
Apache-2.0 (Small checkpoint); CC-BY-NC-4.0 (Base and Large checkpoints)
Code de LibreYOLO
MIT
Poids
Apache-2.0 (s); CC-BY-NC-4.0 (b, l), republiés sur huggingface.co/LibreYOLO
Interprétation
The licence depends on the size. The s checkpoint (Video-Depth-Anything-Small) is Apache-2.0, a permissive license that allows commercial and closed-source use if you keep the license text and notices. The b and l checkpoints (Base and Large) are CC BY-NC 4.0: attribution is required and commercial use is not allowed. The vendored code is Apache-2.0 from DepthAnything/Video-Depth-Anything at commit 4f5ae23172ba60fd7bc11ef671cca678842c7072 (Copyright ByteDance), including a motion module from AnimateDiff and attention code from Hugging Face diffusers, both Apache-2.0; the DINOv2 encoder and DPT head are shared with LibreYOLO's Depth Anything V2 family, and LibreYOLO's own adapter and streaming stitcher are MIT (libreyolo/models/video_depth_anything/NOTICE). LibreYOLO mirrors the converted checkpoints, tensors unchanged, as LibreYOLO/LibreVideoDepthAnything{s,b,l}-depth with the licence of each upstream size, not gated; metric checkpoints are not hosted.

Video Depth Anything is by ByteDance (DepthAnything/Video-Depth-Anything). The vendored code is Apache-2.0. The licence of the weights depends on the size:

  • s (Video-Depth-Anything-Small): Apache-2.0, commercial use allowed.
  • b and l (Base and Large): CC BY-NC 4.0, non-commercial only. They ship with a non-commercial notice.

LibreYOLO mirrors the converted checkpoints, tensors unchanged, as LibreYOLO/LibreVideoDepthAnything{s,b,l}-depth, not gated.

Citation

@article{video_depth_anything,
  title={Video Depth Anything: Consistent Depth Estimation for Super-Long Videos},
  author={Chen, Sili and Guo, Hengkai and Zhu, Shengnan and Zhang, Feihu and Huang, Zilong and Feng, Jiashi and Kang, Bingyi},
  journal={arXiv:2501.12375},
  year={2025}
}

Copié depuis le bloc de citation des auteurs sur github.com/DepthAnything/Video-Depth-Anything#citation.

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.