| license: cc-by-nc-4.0 | |
| tags: | |
| - mlx | |
| - depth-estimation | |
| - video-depth-anything | |
| # Video Depth Anything Base (MLX) | |
| MLX port of [Video Depth Anything](https://github.com/DepthAnything/Video-Depth-Anything) (ByteDance, CVPR 2025 highlight): consistent monocular depth estimation for arbitrarily long videos. Converted from the official checkpoint [`depth-anything/Video-Depth-Anything-Base`](https://huggingface.co/depth-anything/Video-Depth-Anything-Base). | |
| Architecture: DINOv2 backbone + DPT head with AnimateDiff-style temporal motion modules. Outputs per-frame depth maps, not text. | |
| ## Usage | |
| ```python | |
| from mlx_vlm import load | |
| from mlx_vlm.models.video_depth_anything.generate import ( | |
| VideoDepthPredictor, | |
| read_video_frames, | |
| ) | |
| model, processor = load("mlx-community/Video-Depth-Anything-Base-MLX") | |
| predictor = VideoDepthPredictor(model, processor) | |
| frames, fps = read_video_frames("input.mp4", max_len=300, target_fps=15) | |
| depths = predictor.infer(frames) # (T, H, W) float32 | |
| ``` | |
| ## Notes | |
| - Inputs are channel-last `(B, T, H, W, 3)`; H and W must be multiples of 14. | |
| - Metric model: no. Metric models output absolute depth (meters) and skip scale/shift window alignment. | |
| - Weights are fp32. On GPU, output matches the PyTorch reference to ~1% relative (Metal fast-math); on CPU to ~1e-5. | |
| ## License | |
| CC-BY-NC-4.0 (same as the source checkpoint). Non-commercial use only. | |