Introduced at IBC 2026

Real-time AI that balances bright sunlight and deep shadows in live outdoor sports broadcasts.

A processing layer on your camera feeds or program output, for better visibility in real time, from live football to rugby, cricket, tennis and golf. Keep your existing cameras. Processing runs on GPU infrastructure. Non-generative AI: nothing is added or invented, and no artifacts.

LivePictureAI™ was introduced at IBC 2026. We are now validating the technology with selected partners ahead of commercial deployment.

Book a demoWatch the film
SDINDISMPTE ST 2110RTSPUp to 4K60Full specifications
Before: Sports footage with harsh sunlight, shadows and lighting issuesAfter: AI-enhanced sports footage with balanced lightingOriginal✦ LivePictureAI

Drag to compare original vs. enhanced, same frame.

  • Max 100 ms

    added latency, end-to-end

    Under 5 ms processing per frame at 1080p60

  • SMPTE 2110 · NDI · SDI · RTSP

    native signal formats

    Up to 4K60

  • No new cameras

    GPU inference, on-prem or cloud

  • Member of

    NVIDIA Inception ProgramMicrosoft for Startups
The Problem

The problem with outdoor sports broadcasts

Mixed sunlight and shadow remain challenging even in professionally shaded productions. Read why in our guide to shadows in live sports.

Harsh sunlight across parts of the pitch or field

Deep shadows and dark zones

Poor visibility in sun and shade areas

Inconsistent exposure across angles

Reduced viewer experience

The Solution

The LivePictureAI™ solution: AI enhancement for the live video feed

LivePictureAI processes the video feed in real time and reduces lighting imbalance before the signal reaches the viewer, on the camera feeds or on the program output. The result: a clearer, broadcast-grade picture, without changing your existing cameras.

Patent pending

AI-enhanced football broadcast with balanced lighting

Curious what a balanced picture is worth to your production? Explore potential savings.

Technology

Built for live broadcast workflows

Real-time inference

Runs live on the feed, frame by frame.

Standards-native

Supports SMPTE 2110, NDI, SDI, RTSP and file-based streams, up to 4K60.

Flexible deployment

Designed for GPU-based edge or production-hub deployment.

Pipeline integration

On each camera feed before the vision mixer, or on the program output.

Low latency

5 to 10 ms processing per frame depending on resolution (under 5 ms at 1080p60), maximum 100 ms end-to-end including I/O and buffering. Built for live broadcast timing.

Broadcast-grade

Architecture designed for broadcast-grade workflows.

No generative AI

Non-generative AI: nothing is added or invented, and no artifacts. We only lift what the camera captured.

A natural look

Viewers should not notice LivePictureAI, only a much better picture. The producer decides how much shadow stays, so it looks real.

Running SMPTE ST 2110 or NMOS yourself? Analyze and generate streams with the 2110 Toolkit. Working with NDI or SDI? See NDI and SDI integration. All hard specs are in one place on broadcast integration, and what the corrected picture looks like is on the natural look.

Workflow

How LivePictureAI fits into your production

Two setups, depending on the size of the production. Either way it adds at most 100 ms of latency and works with your existing cameras.

Before the vision mixer

Large productions

Cameras / feeds
LivePictureAIOne per camera feed
Vision mixer / switcher
Broadcast / stream
The director cuts with the enhanced pictures. Needs more compute: a GPU per camera feed.
On the program output

Smaller productions

Cameras / feeds
Vision mixer / switcher
LivePictureAIOn the program output
Broadcast / stream
One stream to process, so a lighter compute footprint. The cut is made as today and enhanced on the way out.
Use Cases

Where LivePictureAI delivers value

Live football broadcast
Primary use case

Live football broadcasts

  • • Stadiums with mixed sunlight and shadow
  • • Daytime matches
  • • Wide camera shots
  • • Player visibility improvement
Other use cases

Beyond live football

Also applicable to

Any outdoor sport the sun gets in the way of

  • BaseballThe shadow line between a sunlit infield and a shaded mound
  • American footballHard-edged stand shadows crossing the field at afternoon kick-off
  • TennisShadow traveling across an open court as the match runs
  • CricketLong daytime play as the sun tracks right across the ground
  • RugbyThe same stadium geometry and wide shots as football

And the list goes on: golf, cycling, motorsport, athletics, horse racing, alpine skiing. If the sun reaches it, the problem is there. See how it applies to outdoor sports.

Get Involved

Become a validation partner

We're looking for broadcasters, production companies, clubs and rights holders with outdoor sports footage affected by sunlight and shadows. Help us validate LivePictureAI in real-world production environments.

Book a validation call

Discuss your production, lighting challenge and suitability for a validation project.

Book a call →

Evaluate your footage

Tell us about your footage and setup. We'll agree the evaluation scope and how to share the material.

Message us about an evaluation →

Discuss integration

Discuss signal formats, GPU infrastructure and where LivePictureAI could fit in your workflow.

Message us about integration →
Partners

Partner with LivePictureAI

LivePictureAI is designed to complement existing production infrastructure by adding AI-based lighting correction as a processing layer for live outdoor sports feeds.

OB & Production companies

Broadcast infrastructure vendors

Cloud production platforms

Sports technology providers

Clubs & Leagues

Systems integrators

Founder

Founded by a founder and CEO with product and scale-up experience

Andreas Lännerberg

Andreas Lännerberg

Founder & CEO

Former IT Manager at Lime Technologies and founder and CEO of Meetio, acquired by Logitech in 2021. 25+ years building and scaling tech products.

LinkedIn
We're hiring

We're hiring 10x people

An AI-first team where the best get 10x more done with AI. Developers, customer consultants and marketers, based in Sweden, working flexibly and globally.

See open roles
Progress

Technical progress

  • Real-time inference running on local GPU hardware, AWS and Azure

  • Tested on football footage with strong sunlight/shadow contrast

  • Custom model trained on initial proprietary dataset

  • Automatic training

  • Platform supports video file and live-stream processing

Results

Before / after examples

Compare the original footage with the LivePictureAI-processed image.

Hover to see AI enhancement
Backlit Stand - BeforeBacklit Stand - After
Before
✦ AI

Backlit Stand

Hover to reveal

Sunlit Boards - BeforeSunlit Boards - After
Before
✦ AI

Sunlit Boards

Hover to reveal

Overexposed Crowd - BeforeOverexposed Crowd - After
Before
✦ AI

Overexposed Crowd

Hover to reveal

Backlit Signage - BeforeBacklit Signage - After
Before
✦ AI

Backlit Signage

Hover to reveal

FAQ

Frequently asked questions

Does LivePictureAI replace cameras or production systems?
No. LivePictureAI sits as a processing layer in your existing chain: on the camera feeds before the vision mixer, or on the program output. It enhances the signal; it does not replace your hardware.
Is this for live broadcasts or post-production?
Both. The platform is designed for real-time live broadcast use, but the same pipeline can also enhance archived footage and pre-recorded material.
Which sports are supported?
We're starting with football as the primary validation use case. The underlying model architecture generalizes to most outdoor sports affected by mixed lighting, such as rugby, cricket, tennis and golf. Our testing so far has been on football footage.
Does the AI generate or invent anything in the picture?
No. LivePictureAI is non-generative AI: nothing is added or invented, and no artifacts. It only rebalances the light in what the camera actually captured, and the operator decides how much shadow to keep or lift, so the picture stays true to life.
Which signal formats and resolutions are supported?
SDI, NDI, SMPTE ST 2110, RTSP and file-based streams, up to 4K60 (2160p60) as well as 1080p60.
Is the product commercially available?
LivePictureAI was introduced at IBC 2026. We are now validating the technology with selected partners ahead of commercial deployment. Contact us to discuss a validation opportunity for your production or workflow.
Can we test it on our own footage?
Yes, that's exactly what we're looking for. Get in touch via the contact form and we'll set up an evaluation on your material.
For Investors

Investor note

LivePictureAI is validating the technology with selected partners ahead of commercial deployment. We are open to conversations with investors who understand sports media, broadcast infrastructure, AI video, or B2B SaaS.

Contact founder

Contact

For validation, partnerships or investment conversations.

Andreas Lännerberg

Andreas Lännerberg

Founder & CEO

LivePictureAI

Better visibility. Better experience.

In real time.

Get in Touch

Interested in LivePictureAI?

Book a call or send us a message, whichever suits you.

30 minutes Teams link Instant confirmation

Grab 30 minutes with the team and pick a time that suits you. You'll get instant confirmation and a Microsoft Teams link.

See available times

Prefer to write? instead.