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.
- Aufgaben
- depth
- Größen
- s, b, l at 518 px
- Installation
pip install libreyolo- Supportstufe
- Nur Inferenz, seit v1.8.0. Nur Vorhersage, Validierung und Export. Trainingsfunktionen sind nicht verfügbar.
- Upstream
- Video Depth Anything von ByteDance, Apache-2.0 (Small checkpoint); CC-BY-NC-4.0 (Base and Large checkpoints). Publikation, Quelle
- Lizenzen
- Code Apache-2.0, Gewichte Apache-2.0 (s); CC-BY-NC-4.0 (b, l). Kommerzielle Nutzung
Install
Video Depth Anything needs no optional extra.
pip install libreyoloPredict
Weights download from the LibreYOLO Hugging Face mirrors on first use.
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 depthfrom 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)libreyolo predict model=LibreVideoDepthAnythings-depth.pt source=clip.mp4 save=TrueAny 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
| Aufgabe | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Depth | Depth to ONNX: nicht unterstützt | Depth to TorchScript: nicht unterstützt | Depth to ExecuTorch: nicht unterstützt | Depth to TensorRT: nicht unterstützt | Depth to OpenVINO: nicht unterstützt | Depth to Paddle: nicht unterstützt | Depth to MNN: nicht unterstützt | Depth to RKNN: nicht unterstützt | Depth to Axelera: nicht unterstützt | Depth to ncnn: nicht unterstützt | Depth to TFLite: nicht unterstützt | Depth to CoreML: nicht unterstützt | Depth to Core AI: nicht unterstützt |
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
| Datei | Lizenz der Gewichte |
|---|---|
| Depth | |
| LibreVideoDepthAnythings-depth.pt | apache-2.0 |
| LibreVideoDepthAnythingb-depth.pt | cc-by-nc-4.0 |
| LibreVideoDepthAnythingl-depth.pt | cc-by-nc-4.0 |
Jede oben aufgeführte Datei ist heute in der LibreYOLO-Organisation verfügbar und wird bei der ersten Verwendung heruntergeladen.
Licensing
Prüfe die Lizenz im Hugging-Face-Repository der konkreten Gewichte, die du herunterlädst. Jeder Checkpoint in der LibreYOLO-Organisation hat eine Lizenz, und sie ist innerhalb einer Familie nicht immer gleich. Dieses Repository ist die maßgebliche Quelle. Die Zusammenfassung unten beschreibt den Stand bei der letzten Verifizierung dieser Seite.
Dies ist eine Beschreibung der beteiligten Lizenzen und keine Rechtsberatung. Wenn die Antwort kommerziell relevant ist, lies die Lizenzen selbst und hole eigenen Rechtsrat ein.
- Originalarbeit
- Video Depth Anything, ByteDance
- Upstream-Lizenz
- Apache-2.0 (Small checkpoint); CC-BY-NC-4.0 (Base and Large checkpoints)
- Upstream-Quelle
- github.com/DepthAnything/Video-Depth-Anything
- LibreYOLO-Code
- MIT
- Gewichte
- Apache-2.0 (s); CC-BY-NC-4.0 (b, l), erneut unter huggingface.co/LibreYOLO veröffentlicht
- Einordnung
- 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.bandl(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}
}Aus dem Zitierblock der Autoren unter github.com/DepthAnything/Video-Depth-Anything#citation kopiert.