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.

Task
depth
Ukuran
s, b, l at 518 px
Instalasi
pip install libreyolo
Tier dukungan
Hanya inferensi, sejak v1.8.0. Hanya prediksi, validasi, dan ekspor. Fitur pelatihan tidak berlaku.
Proyek upstream
Video Depth Anything oleh ByteDance, Apache-2.0 (Small checkpoint); CC-BY-NC-4.0 (Base and Large checkpoints). Makalah, sumber
Lisensi
Kode Apache-2.0, bobot Apache-2.0 (s); CC-BY-NC-4.0 (b, l). Penggunaan komersial

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

TaskONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
DepthDepth to ONNX: tidak didukungDepth to TorchScript: tidak didukungDepth to ExecuTorch: tidak didukungDepth to TensorRT: tidak didukungDepth to OpenVINO: tidak didukungDepth to Paddle: tidak didukungDepth to MNN: tidak didukungDepth to RKNN: tidak didukungDepth to Axelera: tidak didukungDepth to ncnn: tidak didukungDepth to TFLite: tidak didukungDepth to CoreML: tidak didukungDepth to Core AI: tidak didukung

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

Setiap berkas di atas saat ini tersedia di organisasi LibreYOLO dan diunduh saat pertama kali digunakan.

Licensing

Periksa lisensi di repositori Hugging Face untuk bobot tertentu yang diunduh. Setiap checkpoint di organisasi LibreYOLO memiliki lisensi, dan lisensinya tidak selalu sama dalam satu family. Repositori tersebut adalah sumber resmi. Ringkasan di bawah menjelaskan ketentuan yang berlaku saat halaman ini terakhir diverifikasi.

Ini adalah deskripsi lisensi yang terlibat, bukan nasihat hukum. Jika jawabannya penting secara komersial, baca sendiri lisensinya dan mintalah nasihat dari penasihat hukum Anda.

Karya asli
Video Depth Anything, ByteDance
Lisensi upstream
Apache-2.0 (Small checkpoint); CC-BY-NC-4.0 (Base and Large checkpoints)
Kode LibreYOLO
MIT
Bobot
Apache-2.0 (s); CC-BY-NC-4.0 (b, l), dipublikasikan ulang di huggingface.co/LibreYOLO
Interpretasi
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}
}

Disalin dari blok sitasi penulis di github.com/DepthAnything/Video-Depth-Anything#citation.

Diverifikasi dengan LibreYOLO v1.8.0. Tabel dukungan, checkpoint, dan angka benchmark di halaman ini dihasilkan dari library yang telah dirilis dan bobot yang dipublikasikan, bukan ditulis manual.