RP AIA · an area of the work

Computer Vision — Photo culling

CV-graded creative culling for event photography (a CV2 · image use-case).

BUILDING

The need it answers

An event photographer comes home with thousands of frames and a brutal night ahead — culling by hand, second-guessing every keeper. The best shots get buried, and work that should feel creative becomes drudgery. Photo culling surfaces the keepers in minutes and grades them Gold / Silver / Bronze, so the photographer spends time creating, not sorting.

What it is

This workflow automates photo selection and grading for event photography. It combines pre-trained vision models with iterative human feedback to surface the best frames and grade them Gold / Silver / Bronze — turning thousands of raw shots into a curated set, fast.

The evolutionHow it was distilled — and what shaped it

🌱 Seed
Automate the brutal night of culling thousands of event frames.
← shaped by the manual drudgery that buries the best shots.
🛤 Path
Built a 4-step CV pipeline — label → extract → train → classify (ViT-L + ConvNeXt + LBP) — with a vision-judge grader.
← shaped by proving the pipeline on a real event, end-to-end.
🔀 Pivot
From 'auto-cull' to a human-in-the-loop grader that learns from corrections — Gold / Silver / Bronze, tuned per photographer.
← shaped by taste is personal; the model should learn yours, not impose its own.
💎 Crystal
107 keepers surfaced from a real event; identity tagging + face enrollment — the CV2 image proof-of-concept for the wider platform.
← shaped by one real use-case proving an industry-agnostic architecture.
⭐ Principle
The photographer creates; the machine sorts — and eventually coaches shot-quality live, during the event.
← shaped by augment the human, never replace the eye.

Where we stand todayBuilt & working

What's nextOn the path

★ the moonshot

On-device coverage intelligence that gives photographers real-time shot-quality feedback during the event — not just grading afterwards.

Home
🔊Om
🎙Ask Vision Roadmap