Move Lights in a Photograph in 3D
CVPR Highlight paper from Yale and Adobe, but it's research not a product.

Hardware-timed stepper pulses eliminate CPU jitter for 0.5mm workshop precision; solves real job pain.
Workshop professionals (woodworkers, window framers) who perform repetitive cutting measurements
CNC router systems (Shapeoko, Maslow) · Shopbot precision woodworking tools · Custom workshop automation (Festool guides)
It runs on an ESP32-S3 over BLE 5.3, uses hardware-timed stepper pulses (RMT peripheral, no CPU jitter) to hit 0.5mm accuracy, and pairs with a Bosch GLM laser meter - point, measure, and the ruler moves there. No typing, no transcription errors.
You can also upload cut lists from a file or email and it runs each position in sequence - perfect for batch cutting window profiles where you need the same set of measurements repeated all day.
Open hardware: off-the-shelf linear rails, NEMA 23 closed-loop stepper, inductive homing sensor. Total BOM is about 470 EUR. I sell the firmware, app (Android + desktop), and a step-by-step build guide for 350 EUR.
Video demo: https://youtu.be/GCUHBiIs4Vk
Happy to answer questions about the build or the ESP32 RMT approach to stepper control.
CVPR Highlight paper from Yale and Adobe, but it's research not a product.
Pixel-distance estimation game when dozens of perception-test games already exist online.
Python wrapper for mpmath eigenvalues when numpy.roots loses precision on ill-conditioned polynomials.
Static rule engine on ESP32 publishes conditioned data to NATS without allocating.
Waitlist-only landing page with zero technical substance or working product to evaluate.
Auditable reasoning runtime on ESP32-C3 when most edge AI needs cloud GPUs.