Spectrum — Stop guessing. Start mixing.

The problem

Color theory is simple on paper.
Painful in practice.

Every art student knows the feeling. You see a colour you love. You try to mix it. An hour later you're staring at brown.

I once saw a dreamy purple in a package. I wanted to use that colour in my painting. Even with hundreds of tries I ended up with a dull, muddy purple.

— Marvis Lau Ying Lok, Spectrum designer

⏱

Trial & error

Hours spent mixing, comparing, adjusting — and still missing the target.

💸

Wasted paint

Expensive cadmiums and quinacridones end up in the trash because we can't predict mixes.

💔

Lost creativity

Projects abandoned because the ideal colour feels impossible to reach.

78%

of art students report frustration mixing target colours from memory.

* Spectrum survey · n=42 secondary art students · April 2026

How it works

Three modes.
One brush-stroke smarter.

Photo Math, but for paint. Spectrum turns your camera and screen into a colour lab assistant.

Mode 01

Scan your arsenal

Point your camera at your paint set. Spectrum's AI identifies every shade and builds your personal digital inventory of all 36 colours.

Mode 02

→

Predict the mix

Choose 2–6 paints from your arsenal. Watch the result update live as you adjust ratios. Powered by Kubelka–Munk pigment optics.

Mode 03

Reverse the recipe

Snap a sunset, a flower, anything. Spectrum solves the perfect mix from your 36 paints — with exact ratios and step-by-step instructions.

The science

Real optics.
Real math. Real accuracy.

Spectrum doesn't just guess colours. It models how pigment particles absorb and scatter light at the molecular scale — then solves the inverse problem with perceptual optimization.

Kubelka–Munk Theory

Every pigment is modelled as a pair of data points — how strongly it absorbs light (K) and how strongly it scatters it (S). When two paints mix, their K and S values combine non-linearly, which is why red + green = brown in paint but yellow in light. Spectrum runs this physics in real time.

R_∞ = 1 + (K/S) − √((K/S)² + 2(K/S))

CIEDE2000 Optimization

Once you pick a target colour, Spectrum searches through ~6,000 two- and three-paint combinations in milliseconds. The match score uses CIEDE2000 — the most advanced model of how the human eye perceives colour difference — so the predicted mix matches what you'll actually see.

ΔE₀₀ = √((ΔL'/k_LS_L)² + (ΔC'/k_CS_C)² + (ΔH'/k_HS_H)² + R_T·…)

95%+

predicted colour match within human-perceptible threshold (ΔE < 2.0)

Idea formulation

From muddy purple
to mixing lab.

Spectrum wasn't designed in a vacuum. It came from a real frustration, then four months of iteration. Here's the timeline.

💡

January · Observation

The dreamy purple that became mud

Painting in art class, I tried for two hours to mix a vibrant package purple. Every attempt drifted toward grey-brown. I couldn't tell if I was using the wrong reds, the wrong ratios, or both. I started watching classmates — same problem, every studio session.

User painPersonal story

🔍

February · Research

Why paint mixing breaks intuition

Pigments don't blend like RGB on screens. The Kubelka–Munk theory (1931) describes paint mixing through subtractive scattering and absorption — non-linear math that humans can't compute by eye. Existing apps use additive RGB averaging and produce results painters know are wrong.

Literature reviewKubelka–MunkCIEDE2000

✏️

March · Sketch

Three modes, drawn on paper

Procreate sketches of an arsenal grid (Mode 1), a slider-based mixing interface (Mode 2), and a camera-target recipe view (Mode 3). Refined the flow with my art teacher, who pointed out that students never use just two paints — real recipes have 3 to 5. That feedback became the multi-color slot system.

Hand sketchesTeacher interviewIteration #2

🛠

April · First prototype

Working colour math on a phone

Built the first interactive prototype with live mixing. Discovered that pure RGB blending looks fake — added a subtractive "muddying" coefficient to match how real paint behaves. Implemented the CIEDE2000 search and benchmarked: 95% of test colours produce a match below ΔE 2.0 (the human-perceptible threshold).

HTML/JS prototypeAlgorithm tuning95% accuracy

🎓

May · STEAM integration

From tool to curriculum

Reframed Spectrum as a STEAM learning resource, not just a productivity app. Designed three classroom modules connecting Science (optics), Math (ratios & optimization), Art (theory), Engineering (algorithmic search), and Technology (the AI). Built around real classroom workflows — five-minute warm-ups, paired prediction games, and capstone optimization challenges.

STEAM curriculumLesson plansHatch Awards 2026

Research & evidence

Built on data —
not just a hunch.

Spectrum's design choices are anchored in user research and published learning-science literature.

Distributed practice produces lasting learning, far more than massed practice.

Cepeda, Pashler, Vul, Wixted & Rohrer · Psychological Bulletin (2006)

A meta-analysis of 184 studies showed that spacing learning sessions across time produces dramatically better long-term retention than cramming the same total time into one session. Effect sizes consistently favoured short, repeated exposures over single long sessions.

For Spectrum: daily 2-minute colour mixing in the app outperforms one weekly hour of theory lectures for retaining colour relationships.

Retrieval practice (testing) improves long-term retention more than restudying.

Roediger & Karpicke · Psychological Science (2006)

Students who repeatedly tested themselves on material remembered it dramatically better one week later than students who simply reread the same material. Active retrieval — predicting before checking — strengthens memory more than passive review.

For Spectrum: Mode 1 (predict-then-reveal) and Mode 2 (mix-then-compare) are both retrieval exercises. Students guess the colour, then see the result — every interaction reinforces learning.

Colour perception is fundamentally relational, not absolute.

Josef Albers · Interaction of Color · Yale University Press (1963)

The seminal text in colour pedagogy demonstrated that a colour's perceived hue depends on adjacent colours, not its inherent wavelength. Albers argued that colour theory must be taught through repeated tactile experimentation — not memorisation of abstract rules.

For Spectrum: every mode shows comparative pairs (target vs. mix, before vs. after), making colour relationships the unit of learning, not isolated swatches.

Digital tools for colour-mixing pedagogy reduce material waste and increase confidence.

Spectrum Survey 2026 · n=42 art students · Chiu Chow Association Secondary School

Among surveyed students who tried our 5-day Spectrum pilot: 81% reported feeling more confident reaching a target colour on the first attempt, and 64% reported throwing away fewer mixed batches. Average reported time spent mixing dropped from 14 min to 6 min per session.

For Spectrum: measurable real-world reductions in both frustration and pigment waste.

Competitive landscape

What's already out there —
and where it falls short.

Plenty of apps name colours. None of them know which paints sit in your box. Here's how Spectrum stacks up against the tools real art students reach for today.

Tool	Identify colour	Predict mix	Knows your paints	Real physics	Audio for VIP
📱Eyedropper apps	✓	—	—	—	—
🎨Pantone Connect	✓	—	—	—	—
🖌Adobe Color	✓	—	—	—	—
📺YouTube tutorials	—	Generic	—	—	—
🌈Spectrum	✓	✓	✓	K–M	✓

★

Spectrum is the only tool that constrains every recipe to the painter's actual 36 pigments — and the only one running real Kubelka–Munk physics, not RGB averaging.

🎯

Arsenal-aware mixes

Other apps tell you "add Cobalt Blue." Spectrum knows your box contains Ultramarine — and gives you a recipe that actually works with the paints in front of you.

🔬

Real subtractive physics

Eyedropper apps average pixels in RGB. Spectrum models how pigment particles absorb and scatter light via Kubelka–Munk — the same equations colour scientists have used since 1931.

📚

Designed for the classroom

Pantone is a brand catalogue. Adobe Color is a designer tool. Spectrum is the only one shipped with three plug-and-play STEAM lesson plans for secondary-school art teachers.

♿

Inclusive by default

No other colour tool ships audio-narrated recipes, WCAG-AAA contrast, and CIEDE2000 perceptual scores in the same product. Spectrum is the first.

Repeated-exposure learning

A little, every day,
beats hours once a week.

Spectrum is designed for micro-practice. The app delivers small, daily moments of colour theory through every interaction — turning learning into a habit, not a homework.

Day 1

First scanStudent scans paint set, sees 36 colours arranged by hue.

Day 2

Predict and verify2 minutes mixing predicted vs. actual. First "aha" moment.

Day 5

Reverse-engineeringStudent tries to make orange flower colour. Builds confidence.

Day 14

Intuition formingStudent predicts mixes correctly before opening app. Theory absorbed.

Day 30

MasteryColour theory becomes second nature. Confidence in studio practice.

The science is settled. Cepeda et al. (2006) showed that learning gains from spaced practice can be 3× greater than equivalent massed practice. Spectrum is the first colour-theory tool designed around this principle — every interaction is an exposure, every exposure compounds.

STEAM Classroom

More than an app.
A curriculum.

Spectrum was built to live inside the art room. Every tap teaches one of the five STEAM disciplines — and every lesson plan is designed to fit a single 30-minute period, with no extra hardware.

SCIENCE

TECH

ENG

ART

MATH

Why Spectrum is a serious colour-theory tool — not just an app demo

PREDICT · REVEAL

Every interaction is a question with an answer.

The app refuses to just hand students a mix. They commit to a guess first — "what happens if I add 30% Ultramarine?" — and only then see the result. That's retrieval practice, the most evidence-backed learning mechanism in cognitive science (Roediger & Karpicke, 2006). Every interaction in Spectrum is a micro-test, which is why theory sticks instead of sliding off.

FEEDBACK · INSTANT

Mistakes cost zero paint.

In a normal lesson, "try this mix" eats five minutes, half a tube, and a wet sheet of paper. In Spectrum, a wrong guess takes three seconds. That collapses the cycle students need to actually internalise a colour relationship — and frees the teacher to focus on intent and composition instead of refereeing the sink.

SCIENCE-BACKED

Real physics, made visible.

Most colour-theory teaching stops at the colour wheel. Spectrum lets a student literally watch Kubelka–Munk subtractive mixing happen — K and S, absorption and scattering, the reason red + green = mud. That promotes art education from "rule memorisation" to inquiry-based science. The math is in the app; the wonder is in the classroom.

INCLUSIVE

One tool, every learner.

Spectrum surfaces hex codes, numerical ratios, perceptual ΔE scores, and audio recipes — so colour-blind, low-vision, and beginner painters all work from the same shared ground truth. No student is "the one who can't see the difference" any more.

CROSS-DISCIPLINARY

Art class becomes STEAM class — without losing the art.

A single Spectrum exercise can teach a Year 3 student about hue families (Art), the additive/subtractive split (Science), the ratio system (Math), an inverse-search algorithm (Engineering), and how a camera samples colour (Technology) — without ever switching apps or losing the painterly intent of the lesson.

DAILY-PRACTICE

Designed for habit, not homework.

Each mode is short enough to run as a five-minute warm-up. Cepeda et al. (2006) showed that short, repeated exposures across days produce 3× the retention of one long session — and Spectrum is the first colour tool architected around that principle from day one.

What a 30-minute lesson looks like

Every Spectrum module shares the same five-beat rhythm, so students learn the format once and then focus on the colour science itself.

Hook (3 min)

Teacher shows a photo on the board: "What's the exact orange of this lily?" Class debates by eye.

Predict (5 min)

Each student opens Spectrum, writes a guess on paper: "I'd mix Cadmium Red + a little Yellow Ochre, ~70/30." No app help yet.

Reveal (5 min)

Students scan the photo with Mode 3. The app returns its recipe. The gap between guess and answer is the lesson.

Paint (12 min)

Students physically mix their version on a palette. The app's hex value becomes the ground truth they're chasing.

Reflect (5 min)

Quick share-out: whose mix landed closest? Why does Ultramarine pull warm reds toward purple? Theory, embodied.

Module 01

Color Theory 101

30 minBeginnerS1–S3

Hue, saturation, value — practised live in Spectrum's Mix Simulator. Students predict each mix on paper, then mix in-app, then on the palette. Three rounds of retrieval per lesson.

Identify primary, secondary, tertiary colours
Understand HSL space and complementary pairs
Predict mix outcomes before painting (STEAM: Art + Science)

Module 02

Pigment Optics & Light

30 minIntermediateS3–S5

Why does red + green = mud in paint but yellow on a screen? Students compare Spectrum's subtractive predictions against a flashlight RGB demo. The Kubelka–Munk model is exposed as a teaching tool — abstract physics made tangible in 30 minutes.

Distinguish subtractive vs additive colour
Explain absorption and scattering of light
Introduce Kubelka–Munk concepts (STEAM: Science + Tech)

Module 03

Ratios & Optimisation

30 minAdvancedS4–S6

Spectrum's reverse-recipe is a real optimisation search. Students learn how the algorithm finds the lowest "colour error" — and try to beat it by hand on graph paper. Algebra meets art, and the algebra wins.

Apply ratios & proportions to real mixtures
Understand error functions & minimisation
Connect algebra to artistic practice (STEAM: Math + Engineering)

Built for everyone

Accessible by design.

Spectrum is the first colour tool designed primarily for the people most underserved by traditional art education.

Download

Spectrum on your phone.
One tap to install.

No App Store. No Play Store. Just a free, native-feeling experience installed directly from this page.

📱 iPad strongly recommended. iPhone works, but the layout may have minor distortion depending on the model.

iPhone & iPad

Web Clip Profile · iOS 14+

Download for iOS ↓ How to install ↗

Android

Progressive Web App · Chrome / Edge

Install for Android → How to install ↗

Or just try it in your browser — no install needed →

Early access

Be first in line for v1.0.

We're rolling out Spectrum to art classrooms across Hong Kong this autumn. Drop your email and we'll send you an invite the day it goes live.

I'm an art teacher — I want classroom access

✓ You're on the list. We'll be in touch this autumn.

120+ beta sign-ups Autumn 2026 public launch

About

Designed by a student,
for students.

Marvis Lau Ying Lok @lokss_is

Designer · Chiu Chow Association Secondary School

Marvis is a Secondary 6 student and the lead designer behind Spectrum. He has spent his secondary school years shaping the visual identity of his school community — designing logos, banners, and apparel for student societies and athletic teams.

Beyond the school walls, he serves as Chief Art Director of "Chic Handmade" (潮之手作), a student design collective focused on emotional wellness. He led product design and strategy for Project WeCan's "Young Innovators Bazaar" (趁墟做老闆), where his line of plush toys, handmade wallets, and bespoke accessories generated over HKD $30,000 in revenue in three days.

Spectrum is born from a real frustration — the day Marvis tried for hours to mix a dreamy purple from a package and ended up with mud. Drawing on his production design experience, he saw firsthand how wasteful physical colour mixing can be for students. He set out to build the tool he wishes he'd had — and turn it into a STEAM learning resource for everyone who paints.

Selected work & recognition

2026PolyU Design Hatch Awards 2026 · Finalist (#32 Spectrum)

2025Chief Art Director · Chic Handmade (潮之手作) emotional-wellness collective

2025Project WeCan "Young Innovators Bazaar" — HKD $30,000+ revenue in 3 days

2024Lead Designer · Chiu Chow Association Secondary School Student Society

2024Corporate identity & apparel design for school sports teams

📧 marvislau1005@gmail.com 🎓 Teacher: Hui Yun Ki 🏆 Hatch Awards 2026 · #32