Ver como markdown

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.

Tarefas
depth
Tamanhos
s, b, l at 518 px
Instalação
pip install libreyolo
Nível de suporte
Somente inferência, desde a v1.8.0. Somente predição, validação e exportação. Os recursos de treinamento não se aplicam.
Origem
Video Depth Anything por ByteDance, Apache-2.0 (Small checkpoint); CC-BY-NC-4.0 (Base and Large checkpoints). Artigo, código-fonte
Licenças
Código Apache-2.0, pesos Apache-2.0 (s); CC-BY-NC-4.0 (b, l). Uso comercial

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

TarefaONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
DepthDepth to ONNX: incompatívelDepth to TorchScript: incompatívelDepth to ExecuTorch: incompatívelDepth to TensorRT: incompatívelDepth to OpenVINO: incompatívelDepth to Paddle: incompatívelDepth to MNN: incompatívelDepth to RKNN: incompatívelDepth to Axelera: incompatívelDepth to ncnn: incompatívelDepth to TFLite: incompatívelDepth to CoreML: incompatívelDepth to Core AI: incompatível

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

Todos os arquivos acima existem hoje na organização LibreYOLO e são baixados no primeiro uso.

Licensing

Confira a licença no repositório do Hugging Face correspondente aos pesos que você baixar. Cada checkpoint na organização LibreYOLO tem uma licença, e ela nem sempre é a mesma em toda a família. Esse repositório é a fonte oficial. O resumo abaixo descreve o que se aplicava na última verificação desta página.

Esta é uma descrição das licenças envolvidas, não uma orientação jurídica. Se a resposta tiver importância comercial, leia as licenças e procure sua própria assessoria.

Trabalho original
Video Depth Anything, ByteDance
Licença original
Apache-2.0 (Small checkpoint); CC-BY-NC-4.0 (Base and Large checkpoints)
Código do LibreYOLO
MIT
Pesos
Apache-2.0 (s); CC-BY-NC-4.0 (b, l), republicado em huggingface.co/LibreYOLO
Interpretação
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}
}

Copiado do bloco de citação dos autores em github.com/DepthAnything/Video-Depth-Anything#citation.

Verificado com o LibreYOLO v1.8.0. As tabelas de suporte, os checkpoints e os números de benchmark desta página são gerados a partir da biblioteca lançada e dos pesos publicados, não escritos à mão.