Phaseform is going to VISION 2026 in Stuttgart, the world’s leading trade fair for machine vision. From 6 to 8 October 2026 you will find us at Hall 8, Stand E60.19, in Start-up World at Messe Stuttgart.

VISION is where the machine vision industry meets: camera and sensor manufacturers, lens makers, illumination specialists, system integrators and the OEMs who turn all of it into inspection, robotics and quality-control systems. For us the show marks a deliberate step — taking adaptive optics out of the research microscope and into industrial imaging.

Why machine vision, and why now

Optical aberrations are a hidden cost driver in imaging systems. They force additional lens elements, tighter assembly tolerances and expensive active alignment — and they cost yield. Worse, once a system is assembled, a fixed lens cannot adapt: not to a residual manufacturing error, not to thermal drift, not to a new working distance.

The Deformable Phase Plate (DPP) changes that premise. It is a thin, fully transmissive wavefront modulator with 63 electrostatically controlled degrees of freedom — a programmable optical surface that corrects and shapes higher-order aberrations directly in the transmission path. It is polarization-independent, low-power, and thin enough to sit inside a compact objective.

Optics that ships with an algorithm

A high actuator count is exactly what makes the DPP a natural counterpart for machine learning. At Photonics West in January 2026 our team presented ML-based open-loop control trained on more than 3,000 closed-loop wavefronts: the model maps a target wavefront straight to 63 electrode voltages and cuts residual error by half or more — from 64 to 22 nm RMS for pure Zernike modes and from 74 to 34 nm RMS for mixed modes. Calibration-based, sensorless correction while the system is running.

Where that leads is nicely illustrated by “Fovea Stacking” (Mao, Mishra & Heidrich, KAUST; ACM Transactions on Graphics 44(6), 2025), Best Paper at SIGGRAPH Asia 2025: a simple lens paired with an ML-controlled DPP steers a region of diffraction-limited sharpness across the field of view — a computational camera built on our Delta 7 SDK. Complexity migrates out of precision-manufactured glass and into software.

What you can see at our stand

  • Delta 7-10 and Delta 7-20 — our transmissive wavefront modulators with 10 mm and 20 mm clear aperture.
  • Phinden — image-based aberration measurement, no wavefront sensor required.
  • Fovea Stacking — live demo. The computational-camera approach from Mao, Mishra and Heidrich at KAUST, built on the Delta 7 SDK: a simple lens plus an ML-controlled DPP steering a region of diffraction-limited sharpness across the field of view.

Two talks at the show

Industrial VISION Days — Tuesday 6 October, on the VISION Days stage (Hall 8, C70). Our CTO Pouya Rajaeipour presents Algorithm-Driven Optics: 63 Degrees of Freedom for AI-Controlled Imaging in the start-up session, 15:20 to 16:00. The talk picks up exactly where the section above leaves off: what changes in optical design once the corrective element has 63 independently addressable degrees of freedom and an algorithm driving them.

EPIC Technology Meeting on Photonics for Computer Vision Systems and Applications — Wednesday 7 October, 10:00 to 12:00. Our CEO Stefan Weber speaks at the EPIC technology meeting in Congress West, room W3.

For OEMs, the interesting conversation is about integration: relaxing tolerances, reducing lens count, correcting residual errors after assembly to raise production yield, and adding dynamic optical functionality under software control. If you design imaging systems and any of that sounds like a problem you recognize, we should talk.

Come by Hall 8, Stand E60.19 — or request a meeting to book a slot in advance.