ScubAI on ScubAI knowledge base

The Problem

Mon, 01 Jan 0001 00:00:00 +0000

The Problem#

Underwater photography sits at the intersection of two hard problems: the physics of light in water, and the reality of being a diver with a camera. Most tools solve one while ignoring the other.

Underwater, simplicity is everything#

A diver is managing buoyancy, air supply, depth, navigation, and buddy awareness — all at once, all the time. Photography has to fit into whatever attention is left. The camera that works underwater is the one that demands the least from the diver.

The Solution

Mon, 01 Jan 0001 00:00:00 +0000

The Solution#

The problems are clear: diving demands your full attention, phone camera apps aren’t built for water, and the physics of underwater light makes every photo come out wrong. ScubAI is an iPhone app designed around all three.

One tap to shoot#

The camera is a full-screen viewfinder — the ocean is the subject, not the UI. No menus, no settings, no decisions. Tap once to capture RAW automatically, preserving the full sensor data.

Under the Hood

Mon, 01 Jan 0001 00:00:00 +0000

Under the Hood#

The Solution described what ScubAI does for the photographer. This article covers how — the processing pipeline, the image analysis, and the controls available for fine-tuning.

Why RAW#

Everything starts with RAW. The case for shooting RAW is stronger underwater than anywhere else: the attenuated red channel may carry a signal so faint that a JPEG discards it entirely, but at 14-bit depth that signal is real and recoverable.

What's Next

Mon, 01 Jan 0001 00:00:00 +0000

What’s Next#

ScubAI started simple — capture RAW, analyze the image, correct the colors. That already solves the core problem: shoot underwater, get the colors back. But the physics allows more, and we’re actively researching and developing several directions to push the correction further.

Scene depth estimation#

The current correction is global — one set of adjustments for the entire image. But objects in a photograph sit at different distances from the camera, and each distance means a different amount of color loss. Correcting accurately requires knowing how far each part of the scene is.