---
license: apache-2.0
base_model: depth-anything/Depth-Anything-V2-Large
tags:
  - robotics
  - edge-deployment
  - anima
  - forge
  - depth-estimation
  - monocular-depth
  - safetensors
  - vision
  - ros2
  - jetson
  - real-time
library_name: transformers
pipeline_tag: depth-estimation
model-index:
  - name: depth-anything-v2-large
    results:
      - task:
          type: depth-estimation
        metrics:
          - name: Model Size (MB)
            type: model_size
            value: 1279
---

# Depth Anything V2 Large — SafeTensors

> Depth Anything V2 (Large, ViT-L backbone) converted to SafeTensors format for safe, fast loading in robotic depth estimation pipelines. 335M parameters for high-quality monocular depth maps.

This model is part of the **[RobotFlowLabs](https://huggingface.co/robotflowlabs)** model library, built for the **ANIMA** agentic robotics platform — a modular ROS2-native AI system that brings foundation model intelligence to real robots operating in the real world.

## Why This Model Exists

Monocular depth estimation is fundamental to robotic navigation and manipulation — robots need to know how far away things are from a single camera. Depth Anything V2 produces the highest-quality relative depth maps from a single image. The original weights are distributed as raw `.pth` files. We converted them to SafeTensors format for safe, zero-copy memory-mapped loading.

## Model Details

| Property | Value |
|----------|-------|
| **Architecture** | DPT head + ViT-Large encoder |
| **Parameters** | 335M |
| **Encoder** | ViT-L/14 (DINOv2-based) |
| **Input Resolution** | Flexible (recommended 518×518) |
| **Output** | Dense relative depth map |
| **Training** | Synthetic + real depth labels (multi-stage) |
| **Original Model** | [`depth-anything/Depth-Anything-V2-Large`](https://huggingface.co/depth-anything/Depth-Anything-V2-Large) |
| **License** | Apache-2.0 |

## Included Files

```
depth-anything-v2-large/
├── model.safetensors          # 1.3 GB — Full model weights
└── README.md                  # This file
```

## Quick Start

```python
from safetensors.torch import load_file
import torch

# Load SafeTensors weights
state_dict = load_file("model.safetensors")

# Load into Depth Anything V2 architecture
from depth_anything_v2.dpt import DepthAnythingV2

model = DepthAnythingV2(encoder='vitl', features=256, out_channels=[256, 512, 1024, 1024])
model.load_state_dict(state_dict)
model.to("cuda").eval()

# Predict depth
depth = model.infer_image(image)  # Returns relative depth map
```

### With Transformers

```python
from transformers import AutoModelForDepthEstimation, AutoImageProcessor
import torch

processor = AutoImageProcessor.from_pretrained("depth-anything/Depth-Anything-V2-Large")
model = AutoModelForDepthEstimation.from_pretrained("depth-anything/Depth-Anything-V2-Large")
model.to("cuda").eval()

inputs = processor(images=image, return_tensors="pt").to("cuda")
with torch.no_grad():
    depth = model(**inputs).predicted_depth
```

### With FORGE (ANIMA Integration)

```python
from forge.vision import VisionEncoderRegistry

depth_estimator = VisionEncoderRegistry.load("depth-anything-v2-large")
depth_map = depth_estimator(image_tensor)  # Relative depth map
```

## Use Cases in ANIMA

Depth estimation is critical across ANIMA modules:

- **Obstacle Avoidance** — Real-time depth maps for safe navigation
- **Grasp Planning** — Estimate object distance for manipulation reach calculations
- **3D Reconstruction** — Dense depth for point cloud generation from single camera
- **Safety Zones** — Distance-based safety boundaries for human-robot collaboration
- **Path Planning** — Identify traversable spaces and obstacle heights

## Depth Anything V2 Family

| Model | Params | Size | Best For |
|-------|--------|------|----------|
| **[depth-anything-v2-large](https://huggingface.co/robotflowlabs/depth-anything-v2-large)** | **335M** | **1.3 GB** | **Highest quality depth** |
| [depth-anything-v2-small](https://huggingface.co/robotflowlabs/depth-anything-v2-small) | 24.8M | 95 MB | Real-time edge deployment |

## Intended Use

### Designed For
- Monocular depth estimation for robotic navigation
- Dense depth maps for manipulation planning
- Point cloud generation from RGB cameras
- Obstacle detection and distance estimation

### Limitations
- Produces relative (not metric) depth — requires calibration for absolute distances
- Performance degrades on reflective, transparent, or textureless surfaces
- Single-frame estimation — no temporal consistency for video
- Inherits biases from training data distribution

### Out of Scope
- Safety-critical autonomous driving without additional validation
- Medical depth estimation
- Surveillance applications

## Attribution

- **Original Model**: [`depth-anything/Depth-Anything-V2-Large`](https://huggingface.co/depth-anything/Depth-Anything-V2-Large) by TUM & HKU
- **License**: [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0)
- **Paper**: [Depth Anything V2](https://arxiv.org/abs/2406.09414) — Yang et al., 2024
- **Converted by**: [RobotFlowLabs](https://huggingface.co/robotflowlabs) using [FORGE](https://github.com/robotflowlabs/forge)

## Citation

```bibtex
@article{yang2024depth_anything_v2,
  title={Depth Anything V2},
  author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Zhao, Zhen and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
  journal={arXiv preprint arXiv:2406.09414},
  year={2024}
}
```

---

<p align="center">
  <b>Built with FORGE by <a href="https://huggingface.co/robotflowlabs">RobotFlowLabs</a></b><br>
  Optimizing foundation models for real robots.
</p>