Stitch Images

Class: StitchImagesBlockV1

Source: inference.core.workflows.core_steps.transformations.stitch_images.v1.StitchImagesBlockV1

This block combines two related scenes both containing fair amount of details. Block is utilizing Scale Invariant Feature Transform (SIFT)

Type identifier

Use the following identifier in step "type" field: roboflow_core/stitch_images@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
max_allowed_reprojection_error	float	Advanced parameter overwriting cv.findHomography ransacReprojThreshold parameter. Maximum allowed reprojection error to treat a point pair as an inlier. Increasing value of this parameter for low details photo may yield better results..	✅
count_of_best_matches_per_query_descriptor	int	Advanced parameter overwriting cv.BFMatcher.knnMatch k parameter. Count of best matches found per each query descriptor or less if a query descriptor has less than k possible matches in total..	✅

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to Stitch Images in version v1.

• inputs: Blur Visualization, Triangle Visualization, Trace Visualization, Label Visualization, Distance Measurement, Pixel Color Count, Absolute Static Crop, Image Preprocessing, Relative Static Crop, Image Threshold, Reference Path Visualization, Stability AI Outpainting, SIFT, Identify Outliers, Stability AI Inpainting, Background Color Visualization, Circle Visualization, Image Blur, Keypoint Visualization, SIFT Comparison, Image Convert Grayscale, Line Counter Visualization, Model Comparison Visualization, Image Slicer, Line Counter, Crop Visualization, Corner Visualization, Pixelate Visualization, Image Slicer, Mask Visualization, Color Visualization, Clip Comparison, Polygon Visualization, Perspective Correction, Detections Consensus, Camera Calibration, Bounding Box Visualization, Camera Focus, Dynamic Crop, Depth Estimation, Halo Visualization, Dot Visualization, Template Matching, Classification Label Visualization, SIFT Comparison, Stability AI Image Generation, Ellipse Visualization, Image Contours, Line Counter, Identify Changes, Grid Visualization, Stitch Images, Polygon Zone Visualization
• outputs: Blur Visualization, Anthropic Claude, Triangle Visualization, Dominant Color, YOLO-World Model, Trace Visualization, Label Visualization, LMM, Roboflow Dataset Upload, Time in Zone, Pixel Color Count, Absolute Static Crop, Image Preprocessing, Keypoint Detection Model, Relative Static Crop, Image Threshold, Reference Path Visualization, Segment Anything 2 Model, QR Code Detection, Stability AI Outpainting, SIFT, Instance Segmentation Model, Roboflow Dataset Upload, Google Vision OCR, Stability AI Inpainting, Background Color Visualization, Detections Stabilizer, Keypoint Visualization, Circle Visualization, Image Blur, VLM as Detector, Google Gemini, OpenAI, Image Convert Grayscale, Line Counter Visualization, Multi-Label Classification Model, Model Comparison Visualization, Perception Encoder Embedding Model, Image Slicer, Crop Visualization, Corner Visualization, VLM as Classifier, Multi-Label Classification Model, Pixelate Visualization, Image Slicer, Mask Visualization, VLM as Classifier, Clip Comparison, Color Visualization, Qwen2.5-VL, Polygon Visualization, Keypoint Detection Model, Single-Label Classification Model, Gaze Detection, Perspective Correction, Moondream2, Camera Calibration, OpenAI, Bounding Box Visualization, Barcode Detection, Buffer, Camera Focus, SmolVLM2, CogVLM, Instance Segmentation Model, Detections Stitch, OpenAI, Dynamic Crop, Halo Visualization, Depth Estimation, Florence-2 Model, Dot Visualization, Template Matching, Classification Label Visualization, SIFT Comparison, Stability AI Image Generation, Florence-2 Model, VLM as Detector, LMM For Classification, Object Detection Model, Ellipse Visualization, Llama 3.2 Vision, Image Contours, Clip Comparison, Single-Label Classification Model, Stitch Images, OCR Model, CLIP Embedding Model, Byte Tracker, Object Detection Model, Polygon Zone Visualization

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Stitch Images in version v1 has.

Bindings

• input

  • image1 (image): First input image for this step..
  • image2 (image): Second input image for this step..
  • max_allowed_reprojection_error (float_zero_to_one): Advanced parameter overwriting cv.findHomography ransacReprojThreshold parameter. Maximum allowed reprojection error to treat a point pair as an inlier. Increasing value of this parameter for low details photo may yield better results..
  • count_of_best_matches_per_query_descriptor (integer): Advanced parameter overwriting cv.BFMatcher.knnMatch k parameter. Count of best matches found per each query descriptor or less if a query descriptor has less than k possible matches in total..

• output

  • stitched_image (image): Image in workflows.

Example JSON definition of step Stitch Images in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/stitch_images@v1",
    "image1": "$inputs.image1",
    "image2": "$inputs.image2",
    "max_allowed_reprojection_error": 3,
    "count_of_best_matches_per_query_descriptor": 2
}