Deconvolution

This function block helps restore sharpness and detail in images—especially useful for images of fast-moving objects that appear blurred. Use the provided sliders to tune the restoration effect for your camera and scene.

📥 Inputs

Image Any (input socket) A color or grayscale image to be processed.

📤 Outputs

Image Any (output socket) The processed image with deconvolution applied.

🕹️ Controls

Angle Adjusts the direction or orientation of the deconvolution effect. Useful when motion blur has a predominant direction.

Diameter Controls the size/strength of the correction area. Higher values affect larger blur kernels.

Noise Reduction Controls how aggressively noise is reduced while restoring detail. Increasing this reduces noise but may soften fine detail.

🎨 Features

• Restores sharpness for motion-blurred images while allowing user control over direction and strength.

• Works with both grayscale and color images (color images are processed per channel).

• Simple sliders make it easy to experiment without technical knowledge.

⚙️ Running mechanism

When the block runs it accepts the incoming image, applies the deconvolution processing (taking into account the chosen Angle, Diameter, and Noise Reduction values) and outputs the corrected image. If a color image is provided, each color channel is handled so the final output keeps correct color information.

📝 Usage Instructions

1. Connect a camera or image source to the Image Any input.

2. Start with moderate values: set Angle to match the motion direction (if known), set Diameter to a small/medium value, and set Noise Reduction low.

3. Inspect the result and adjust sliders until the image looks sharp without excessive artifacts.

4. Use the output image downstream (display, save, measurement, etc.).

💡 Tips and Tricks

• Combine with Denoising before this block to reduce sensor noise and avoid amplifying noise during deconvolution.

• If the input image is very large, use Image Resize to lower the resolution for faster experimentation, then re-run at full size for final results.

• Use Image ROI to crop to the area of interest before processing—this speeds up tuning and prevents over-processing irrelevant areas.

• If contrast is low, try Contrast Optimization prior to deconvolution to make details more recoverable.

• Use Show Image to preview results quickly, and Image Logger to save processed frames for later review.

🛠️ Troubleshooting

• Output looks noisy or has artifacts: increase Noise Reduction or place a Denoising block before deconvolution.

• No visible improvement: try changing Angle to match motion direction and increase Diameter gradually.

• Processing is slow: reduce image size with Image Resize or limit processing to a region with Image ROI.

• Colors look off after processing: confirm you started with a color image and preview using Show Image; if necessary, adjust the pipeline order (e.g., apply Contrast Optimization before deconvolution).