Depth Estimation¶
Class: DepthEstimationBlockV1
Source: inference.core.workflows.core_steps.models.foundation.depth_estimation.v1.DepthEstimationBlockV1
🎯 This workflow block performs depth estimation on images using Apple's DepthPro model. It analyzes the spatial relationships
and depth information in images to create a depth map where:
📊 Each pixel's value represents its relative distance from the camera
🔍 Lower values (darker colors) indicate closer objects
🔭 Higher values (lighter colors) indicate further objects
The model outputs:
1. 🗺️ A depth map showing the relative distances of objects in the scene
2. 📐 The camera's field of view (in degrees)
3. 🔬 The camera's focal length
This is particularly useful for:
- 🏗️ Understanding 3D structure from 2D images
- 🎨 Creating depth-aware visualizations
- 📏 Analyzing spatial relationships in scenes
- 🕶️ Applications in augmented reality and 3D reconstruction
⚡ The model runs efficiently on Apple Silicon (M1-M4) using Metal Performance Shaders (MPS) for accelerated inference.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/depth_estimation@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
model_version |
str |
The Depth Estimation model to be used for inference.. | ✅ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow runtime. See Bindings for more info.
Runtime compatibility¶
-
hard— runtimeself_hosted_cpu; executionlocal - Requires a GPU; run_locally() loads a model that needs CUDA.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Depth Estimation in version v1.
- inputs:
Morphological Transformation,Roboflow Asset Library Attributes,Image Preprocessing,Florence-2 Model,Email Notification,VLM As Classifier,Halo Visualization,Morphological Transformation,EasyOCR,Object Detection Model,Twilio SMS Notification,Text Display,Local File Sink,Image Threshold,Icon Visualization,Triangle Visualization,Qwen 3.5 API,Model Monitoring Inference Aggregator,Pixelate Visualization,Keypoint Detection Model,Microsoft SQL Server Sink,Qwen-VL,OpenAI,CogVLM,Crop Visualization,Dot Visualization,Google Vision OCR,OpenRouter,Florence-2 Model,Roboflow Dataset Upload,Qwen3.5-VL,Roboflow Vision Events,Polygon Zone Visualization,Polygon Visualization,OpenAI,Background Color Visualization,Absolute Static Crop,S3 Sink,MoonshotAI Kimi,Twilio SMS/MMS Notification,QR Code Generator,SIFT Comparison,Contrast Enhancement,Google Gemini,Grid Visualization,Corner Visualization,Reference Path Visualization,Image Slicer,Single-Label Classification Model,Stitch OCR Detections,Halo Visualization,Dynamic Crop,Webhook Sink,OCR Model,Color Visualization,Stability AI Outpainting,Roboflow Dataset Upload,Roboflow Custom Metadata,LMM For Classification,OpenAI-Compatible LLM,Relative Static Crop,Image Blur,Line Counter Visualization,Stability AI Inpainting,Blur Visualization,Anthropic Claude,Clip Comparison,Multi-Label Classification Model,Current Time,OpenAI,Perspective Correction,Keypoint Visualization,Llama 3.2 Vision,Anthropic Claude,MQTT Writer,MoonshotAI Kimi,Google Gemini,Image Slicer,Camera Calibration,Model Comparison Visualization,Depth Estimation,Trace Visualization,Ellipse Visualization,Google Gemma,Google Gemma API,OPC UA Writer Sink,Slack Notification,Circle Visualization,Email Notification,LMM,Google Gemini,Instance Segmentation Model,Event Writer,Contrast Equalization,Camera Focus,Heatmap Visualization,Background Subtraction,Image Contours,Qwen 3.6 API,GLM-OCR,VLM As Detector,Classification Label Visualization,Bounding Box Visualization,Label Visualization,Llama 3.2 Vision,Stitch OCR Detections,Camera Focus,CSV Formatter,Stitch Images,Mask Visualization,OpenAI,SIFT,Stability AI Image Generation,Anthropic Claude,Polygon Visualization,Image Convert Grayscale - outputs:
Morphological Transformation,Image Preprocessing,Email Notification,VLM As Classifier,Morphological Transformation,Halo Visualization,Object Detection Model,Pixel Color Count,BoT-SORT Tracker,Template Matching,Image Threshold,Text Display,Pixelate Visualization,Keypoint Detection Model,Qwen-VL,OpenAI,CogVLM,Crop Visualization,SAM 3,Dot Visualization,Google Vision OCR,Florence-2 Model,Roboflow Dataset Upload,Mask Edge Snap,Qwen3.5-VL,Roboflow Vision Events,Polygon Zone Visualization,Qwen2.5-VL,Polygon Visualization,SIFT Comparison,Absolute Static Crop,Twilio SMS/MMS Notification,SIFT Comparison,Contrast Enhancement,Single-Label Classification Model,OCR Model,Byte Tracker,Color Visualization,Roboflow Dataset Upload,Gaze Detection,LMM For Classification,Detections Stabilizer,Line Counter Visualization,Image Blur,Stability AI Inpainting,Object Detection Model,Blur Visualization,SAM 3,Perspective Correction,Keypoint Visualization,Anthropic Claude,MoonshotAI Kimi,Google Gemini,Image Slicer,SAM 3,Depth Estimation,Detections Stitch,Ellipse Visualization,Google Gemma API,Object Detection Model,Time in Zone,Image Stack,Google Gemini,Bounding Box Visualization,Label Visualization,Keypoint Detection Model,Camera Focus,Keypoint Detection Model,Multi-Label Classification Model,OpenAI,SIFT,Perception Encoder Embedding Model,Anthropic Claude,Image Convert Grayscale,Moondream2,OC-SORT Tracker,CLIP Embedding Model,Florence-2 Model,Seg Preview,EasyOCR,YOLO-World Model,Buffer,Multi-Label Classification Model,Segment Anything 2 Model,Single-Label Classification Model,Triangle Visualization,Icon Visualization,Qwen 3.5 API,VLM As Classifier,OpenRouter,Dominant Color,Instance Segmentation Model,Qwen3-VL,Instance Segmentation Model,OpenAI,Background Color Visualization,MoonshotAI Kimi,Google Gemini,Clip Comparison,Semantic Segmentation Model,Corner Visualization,Image Slicer,SmolVLM2,Reference Path Visualization,Single-Label Classification Model,Halo Visualization,Dynamic Crop,Instance Segmentation Model,Stability AI Outpainting,VLM As Detector,Anthropic Claude,Relative Static Crop,Multi-Label Classification Model,Clip Comparison,SORT Tracker,OpenAI,Llama 3.2 Vision,Barcode Detection,ByteTrack Tracker,Motion Detection,Camera Calibration,Google Gemma,Model Comparison Visualization,Trace Visualization,QR Code Detection,Circle Visualization,LMM,Event Writer,Instance Segmentation Model,Contrast Equalization,Camera Focus,Heatmap Visualization,Background Subtraction,Qwen 3.6 API,SAM2 Video Tracker,GLM-OCR,Image Contours,Qwen3.5,VLM As Detector,Classification Label Visualization,Llama 3.2 Vision,Stitch Images,Mask Visualization,Stability AI Image Generation,Semantic Segmentation Model,Polygon Visualization
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Depth Estimation in version v1 has.
Bindings
-
input
-
output
image(image): Image in workflows.normalized_depth(numpy_array): Numpy array.
Example JSON definition of step Depth Estimation in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/depth_estimation@v1",
"images": "$inputs.image",
"model_version": "depth-anything-v2/small"
}