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

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
}