Depth-Anything-V2-Metric-Indoor-Base-hf
depth-anything/Depth-Anything-V2-Metric-Indoor-Base-hf
A popular open depth estimation model, with 5K downloads a month. gigarouter benchmarks and hosts it as an OpenAI-compatible API.
about this model
Model Overview
This is a fine-tuned version of Depth Anything V2 for indoor metric depth estimation, trained on the synthetic Hypersim dataset. It uses the DPT architecture with a DINOv2 backbone and was trained on approximately 600,000 synthetic labeled images and 62 million real unlabeled images, achieving state-of-the-art results for both relative and absolute depth estimation. The model can also be used for zero-shot depth estimation.
Benchmark Performance
Six metric depth models of three scales for indoor and outdoor scenes are available. This model is the base indoor variant (97.5M parameters).
| Base Model | Params | Indoor (Hypersim) | Outdoor (Virtual KITTI 2) |
|---|---|---|---|
| Depth-Anything-V2-Small | 24.8M | Model Card | Model Card |
| Depth-Anything-V2-Base | 97.5M | Model Card | Model Card |
| Depth-Anything-V2-Large | 335.3M | Model Card | Model Card |
Architecture & Training
Introduced in the paper Depth Anything V2, the model uses synthetic data and a larger capacity teacher model to achieve finer and more robust depth predictions compared to the original Depth Anything release.
Depth Anything overview. Taken from the original paper.
We're benchmarking and onboarding Depth-Anything-V2-Metric-Indoor-Base-hf as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.