> For the complete documentation index, see [llms.txt](https://docs.augelab.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.augelab.com/function-blocks/blocks-reference/image-transformations/transformation-filters/denoising.md).

# Denoising

This function block reduces noise in images using a fast non-local means denoising method. It works for both color and grayscale images and provides sliders to balance noise removal and detail preservation.

## 📥 Inputs <a href="#inputs" id="inputs"></a>

`Image Any` Connect an image (color or grayscale) that you want to denoise.

(hint: this is an input socket)

## 📤 Outputs <a href="#outputs" id="outputs"></a>

`Image Any` The denoised image is provided here.

(hint: this is an output socket)

## 🕹️ Controls <a href="#controls" id="controls"></a>

`Strength` Adjusts the overall denoising strength. Higher values remove more noise but may blur fine details.

`Averaging` Controls the averaging power used for smoothing. Increasing this can reduce noise but may soften edges.

`Blend Noise (Colored)` Adjusts color-channel blending for colored images. Use to control how color noise is treated relative to luminance noise.

(hint: these are interactive sliders visible on the block)

## ⚙️ Running Mechanism <a href="#how-it-works" id="how-it-works"></a>

* When the block receives an image through the `Image Any` input, it applies the selected denoising parameters and updates the output with the processed image.
* Parameters are read from the sliders each run, so changing a slider affects the next evaluation.
* The block handles both single-channel and multi-channel images, selecting the appropriate processing automatically.

## ✨ Features <a href="#features" id="features"></a>

* Works for both grayscale and color images.
* Real-time parameter tuning using sliders for instant visual feedback.
* Balanced noise removal to preserve edges when tuned correctly.

## 📝 Usage Instructions <a href="#usage" id="usage"></a>

1. Connect an image-producing block to the `Image Any` input.
2. Adjust `Strength` to control how aggressively noise is removed.
3. Fine-tune `Averaging` to manage smoothness versus detail.
4. For color images, tweak `Blend Noise (Colored)` to adjust color-specific denoising.
5. Observe the denoised result from the `Image Any` output (connect to a viewer or saver).

## 💡 Tips and Tricks <a href="#tips-and-tricks" id="tips-and-tricks"></a>

* For noisy camera captures, try combining this block with `Bilateral Filter` or `Blur` before denoising to reduce impulse noise and make results cleaner.
* Use `Show Image` to preview results live while you tune sliders.
* To save examples for later comparison, connect the output to `Image Logger` or `Image Write`.
* If you want to keep a stable frame for comparison during tweaking, use `Image Memory` to freeze a chosen frame while you adjust controls.
* Crop to the region of interest first with `Image ROI Select` to focus denoising only where it matters and save compute.

(hint: recommended complementary blocks are listed above for common workflows)

## 🛠️ Troubleshooting <a href="#troubleshooting" id="troubleshooting"></a>

* If the result looks overly smooth or details are lost: lower the `Strength` and reduce `Averaging`.
* If color artifacts appear after denoising: reduce `Blend Noise (Colored)` or try preprocessing with `Blur`.
* If performance is slow on large images: resize with `Image Resizer` or process smaller ROIs via `Image ROI Select`.

If you need more visual debugging while tuning, connect the output to `Show Image` to inspect changes frame-by-frame.