IRIS.AI

Wavelet Beam proudly presents IRIS.AI: Advanced AI-Based Video Upscaling


Before applying AI-driven upscaling, it's critical to first denoise the video. Why? Because noise in the original footage can confuse AI algorithms, leading to artifacts and reduced visual quality in the final result.


IRIS.AI combines Wavelet Beam's cutting-edge video denoising with powerful deep learning upscaling to ensure exceptional results. Clean input means the AI can focus on real image content, not on random noise, resulting in sharper, more natural details and improved resolution.


By preprocessing with IRIS, IRIS.AI receives a cleaner signal, allowing the upscaler to add pixels more accurately. The result: enhanced visual quality, higher perceived resolution, and a stunning viewing experience, ideal for remastering, broadcasting, or archive restoration.


IRIS.AI Upscaling Example 1

IRIS.AI Upscaling Example 2

Results and Insights

Measurements and findings from our work, summarized from Dirk Hildebrandt's posts and articles.

  1. Why denoise before upscaling

    If a video contains noise, the upscaling algorithm can misinterpret it as image detail and create artifacts. Removing the noise first gives the AI a cleaner input for better results and can also reduce the computational effort of upscaling.

    Read on LinkedIn
  2. Ready for UHD displays

    UHD televisions upscale every SD and HD signal, and noise and other artifacts become more visible in the process. High-fidelity pre-processing turns HD material into content that looks its best on UHD screens.

    Read on LinkedIn

Frequently Asked Questions

Why denoise before AI upscaling?

Because the upscaler would otherwise interpret noise as image detail and create artifacts. A clean input lets the AI add real detail.

Which content benefits most?

Archive material, remastering projects and any SD or HD content that is shown on large UHD screens.

Is IRIS.AI available as a service?

Yes, IRIS.AI runs fully automated on clusters, in the cloud or on-premises, and as a SaaS workflow with per-minute pricing.