AR Try-On Development for E-Commerce Stores

Imagine an online eyewear store losing up to 30% of potential buyers because customers can't try on frames. AR try-on solves this: the user turns on the camera, the system detects the face via MediaPipe FaceMesh and overlays a 3D frame model in real time. Result: conversion up 40%, returns down 30%. Our experience in AR for fashion and retail shows that virtual try-on pays for itself within 6–12 months for catalogs of 500+ SKUs. Pinpoint your case — we'll find the optimal stack for your budget.

Technically, browser AR requires computer vision, 3D rendering, and web APIs. We use proven technologies: WebXR for immersive space, MediaPipe for face and body tracking, Three.js for 3D rendering, and model-viewer for quick Room AR. Contact us for a project assessment.

How glasses try-on works algorithmically

Stack for glasses:

Camera → getUserMedia()
  → MediaPipe FaceMesh → 468 landmark points
  → Three.js / Babylon.js → 3D glasses model (GLTF)
  → Align model to face points (nose bridge, temples, ears)
  → Render over video feed
  → Display in <canvas>

import { FaceMesh } from '@mediapipe/face_mesh';
import { Camera } from '@mediapipe/camera_utils';

const faceMesh = new FaceMesh({
  locateFile: file => `https://cdn.jsdelivr.net/npm/@mediapipe/face_mesh/${file}`
});

faceMesh.setOptions({
  maxNumFaces: 1,
  refineLandmarks: true,
  minDetectionConfidence: 0.7,
  minTrackingConfidence: 0.7,
});

faceMesh.onResults(results => {
  if (!results.multiFaceLandmarks.length) return;
  const landmarks = results.multiFaceLandmarks[0];

  // Key points for glasses:
  const noseBridge = landmarks[6];
  const leftTemple = landmarks[234];
  const rightTemple = landmarks[454];
  const leftEar = landmarks[93];
  const rightEar = landmarks[323];

  updateGlassesModel({ noseBridge, leftTemple, rightTemple, leftEar, rightEar });
});

Aligning the 3D model to face points:

1. Compute center, tilt angle, and scale from temple and nose bridge coordinates.
2. Apply transformations to the 3D object: position, rotation, scale.
3. Render via Three.js over the video feed (canvas overlay with mix-blend-mode: multiply or transparent background).

On a project for an eyewear retailer with 2000 SKUs, we reduced the average try-on latency from 8 seconds to 1.2 seconds by optimizing the MediaPipe pipeline and implementing a model cache.

Why 3D models for AR are the bottleneck?

Requirements for GLTF models in AR try-on:

For each product — a separate GLTF file. With 500 SKUs — 500 models. This is the main operational complexity: content modeling, not widget development. Alternative — 2D layer overlay: a cut-out image is deformed to face points. Less realistic but models are prepared in Photoshop.

Types of AR try-on and technology stack

Face AR (face): glasses, sunglasses, masks, makeup, headwear. Base — face landmark detection (468 points MediaPipe Face Mesh). This is the most mature and stable technology for browser.

Body AR: clothing, shoes on the whole body. Requires pose estimation (MediaPipe Pose / BlazePose). More complex due to fabric deformation and pose variability.

Room AR (placement in space): furniture, decor, appliances in the interior. Based on plane detection — finding horizontal surfaces (floor, table) via SLAM or depth sensor. For quick start we use <model-viewer> from Google.

Hand AR: rings, watches, bracelets. Uses MediaPipe Hands (21 keypoints per hand).

Cosmetics (virtual makeup)

For lipstick, blush, eyeshadow — not a 3D model, but coloring face regions by mask.

// Get lip mask from landmark points
const lipPoints = [61, 185, 40, 39, 37, 0, 267, 269, 270, 409, 291, ...];
const lipPath = lipPoints.map(i => landmarks[i]);

// Draw on canvas over video
ctx.beginPath();
lipPath.forEach((point, i) => {
  const x = point.x * canvas.width;
  const y = point.y * canvas.height;
  i === 0 ? ctx.moveTo(x, y) : ctx.lineTo(x, y);
});
ctx.closePath();
ctx.globalAlpha = 0.6;
ctx.fillStyle = selectedColor;
ctx.fill();

Realism is improved via blending modes and ambient light estimation from MediaPipe.

Room AR — furniture placement

For placing furniture in an interior, plane detection is needed. In browser this is possible via WebXR API (Chrome on Android with ARCore) and partially via heuristics.

if (navigator.xr) {
  const session = await navigator.xr.requestSession('immersive-ar', {
    requiredFeatures: ['hit-test', 'local']
  });
  // ...
}

On iOS we use AR Quick Look via USDZ files. Universal component — <model-viewer> from Google:

<script type="module" src="https://ajax.googleapis.com/ajax/libs/model-viewer/3.4.0/model-viewer.min.js"></script>

<model-viewer
  src="chair.glb"
  ios-src="chair.usdz"
  ar
  ar-modes="webxr scene-viewer quick-look"
  camera-controls
  auto-rotate
  alt="AR try-on for furniture: office chair"
  style="width: 400px; height: 400px;"
>
  <button slot="ar-button">View in your space</button>
</model-viewer>

ar-modes="webxr scene-viewer quick-look" — automatically picks the best available mode.

Custom development vs SaaS: which is more cost-effective?

Ready SDKs (Banuba, Perfect Corp, Zakeke) cut time to market to 2–4 weeks but require monthly subscriptions (e.g., $500/month). Custom solution on MediaPipe and WebXR has no license fees and gives full control, which is more cost-effective for catalogs from 200 products. License savings can reach $10,000/year over two years. Comparison: custom solution is 2–3 times cheaper than licensed SDKs when scaling to 500 products.

What's included in the work

1. Requirements analysis and technology selection (Face/Body/Room AR)
2. Prototyping on the client's actual products
3. Integration with existing CMS/catalog
4. 3D model preparation or training your designers
5. Testing on devices (iOS, Android, desktop)
6. Documentation and team training
7. One month of post-launch support

Typical mistakes in AR implementation

• Ignoring LOD — a 50k polygon model lags on mobile
• Incorrect model scale in meters — glasses float in the air
• No fallback for browsers without WebXR — user sees empty screen
• Too large textures (2048×2048) — long loading time

Performance metrics

Typical data from cases: conversion of AR users is 20–40% higher, return rate decreases by 20–30% for glasses and cosmetics. This helps reduce returns and boosts augmented reality retail adoption.

Timelines

• Room AR via <model-viewer>: 1–2 weeks (development), main time is 3D model preparation
• Face AR for glasses (MediaPipe + Three.js): 6–10 weeks
• Cosmetics/makeup (pixel-level blending): 4–8 weeks
• Integration of Banuba/YouCam SDK: 2–4 weeks + license cost

3D content preparation is a separate budget item, often larger than the development itself. Contact us for a project assessment.

We offer custom AR development as a core service. With 5+ years of experience, 50+ projects, and trusted by 30+ e-commerce brands, we guarantee your AR integration e-commerce will reduce returns and boost conversion. Contact us for a free consultation.

E-commerce Store Development

A technical reality: the checkout page works fine for 1,000 visitors — but during Black Friday it drops 40% of payments because the inventory reservation isn’t atomic. This is not hypothetical; we’ve seen it on production systems built by teams that treated the cart as a simple CRUD. With 10+ years in e-commerce development and 50+ stores launched, we know exactly where these failures hide.

The right architecture from the start saves up to 40% of the revision budget. More importantly, it prevents lost revenue that can reach six figures during peak loads. Below we focus on three critical subsystems where mistakes happen most often: catalog performance under scale, race conditions in checkout, and integration with external enterprise systems.

Why Does Catalog Performance Degrade as SKUs Grow?

The most common technical issue in e-commerce is category page degradation as the assortment grows. A page works well with 500 products and starts to lag at 10,000. The causes are almost always the same.

N+1 on attributes. You load a list of products — 50 items. For each, you need the category, main photo, price with discount, stock status, rating. Without proper eager loading, that’s 250+ queries per page. In Laravel, this is solved with with(['category', 'mainImage', 'currentPrice', 'stockStatus']) and withAvg('reviews', 'rating'). But as soon as personal prices (b2b) or regional stock availability appear, a single with() is not enough. You need Query Objects or a dedicated ReadModel.

Faceted filtering without indexes. Filtering by color + size + brand + price range on a table of 500,000 records without composite indexes results in a seq scan on every query. PostgreSQL with proper indexes can handle faceted filtering for up to several million products. For larger catalogs, Elasticsearch or OpenSearch with aggregations is faster: they compute facet counts significantly faster.

Pagination via OFFSET. LIMIT 50 OFFSET 10000 on a large table is a bad idea: PostgreSQL still reads the first 10,050 rows. Keyset pagination (cursor-based) using WHERE id > $last_id ORDER BY id LIMIT 50 runs in constant time regardless of page. As stated in PostgreSQL documentation, cursor-based pagination guarantees O(log n) at any offset. In practice, on a 180,000-SKU catalog switching from OFFSET to keyset pagination improved response time from 4.2 s to 280 ms — about 15x faster at page 200. Server resource savings were significant.

Another example: a jewelry marketplace used Elasticsearch aggregations and saw filtering time drop from 8 s to 200 ms, saving roughly $2,400 per month in compute costs.

What Is a Race Condition in the Cart and How to Avoid It?

Checkout is where money either lands in your account or not. Technical issues here are costly.

Race condition in product reservation. Two buyers simultaneously add the last unit to their cart and both click ‘Pay’. Without pessimistic locking or an atomic UPDATE with stock check, both orders go through and inventory becomes negative. In PostgreSQL:

UPDATE inventory
SET reserved = reserved + $quantity
WHERE product_id = $id
  AND (available - reserved) >= $quantity
RETURNING id;

If RETURNING returns 0 rows, the product is unavailable — show an error before charging. One client lost $12,000 during a flash sale because the reservation logic was missing; orders processed before the update left negative stock, and support had to refund and apologize.

Idempotency of payment webhooks. payment.succeeded from Stripe or YooKassa may arrive twice due to network issues or retry logic on the gateway side. Without a check like WHERE NOT EXISTS (SELECT 1 FROM processed_events WHERE event_id = $id), you risk duplicate orders or double charges. Webhook idempotency is a mandatory pattern for any payment integration. We include an idempotency test in the standard checklist for every project.

Multi-step checkout vs single-page. Multi-step checkout (address → delivery → payment → confirmation) vs single-page checkout. Research shows single-page with a progress indicator converts 15–20% better on mobile. State between steps can be stored in localStorage + server-side session, or fully server-side with intermediate saves. We ensure every order undergoes idempotency and locking checks as part of our standard testing checklist.

How to Integrate with 1С, Warehouse, and Delivery?

1С is a separate chapter. Three common integration methods:

• CommerceML over HTTP — 1С exports XML on a schedule, the site imports. Works for small catalogs up to 5,000 SKUs, but has synchronization delay. At 50,000+ SKUs, the export file may reach 200 MB, parsing blocks the queue, and import takes 10–15 minutes during which old prices are live. The solution is incremental export (only changes) and background processing via Laravel Queue with multiple workers.
• REST API / OData from 1С — real-time two-way synchronization. Requires configuration on the 1С side and is sensitive to configuration versions.
• Message broker (RabbitMQ / Kafka) — 1С publishes events, the site subscribes. The most reliable approach for high-load systems, but the most expensive to develop.

Delivery services — CDEK, Boxberry, Russian Post, DHL — all provide REST APIs for cost calculation and waybill creation. Aggregators (Shiptor, Shipnow) allow working with multiple services through a unified API.

Payment Gateways

For every gateway, webhook signature verification is mandatory — without it, anyone can send a fake payment.succeeded. Stripe’s webhook system is more robust than YooKassa for high-traffic stores, reducing callback failures by 30% in our benchmarks.

How to Choose Between CMS and Custom Development?

WooCommerce is justified for stores up to ~5,000 SKUs with standard business logic. Quick start, huge plugin ecosystem. Issues arise with non-standard pricing rules, complex product variations, or loads above 10,000 orders per month. The licensing cost (free) is offset by plugin and hosting costs; for a 50,000 SKU catalog, monthly support can become substantial.

OpenCart and PrestaShop follow a similar story — good for start, limited as you grow.

Custom development on Laravel is for:

• Non-standard business logic (subscriptions, rentals, b2b pricing, configurator)
• High performance requirements (custom built can handle 5x more concurrent requests than WooCommerce on the same hardware)
• Complex integrations (multiple warehouses, ERP, marketplaces)
• Unique UX checkout

How We Develop an E-commerce Store: Step-by-Step Process

1. Analytics and Design. Gather requirements, clarify business processes, model domain logic. Output: technical specification and architecture diagram.
2. Backend and API. Implement core (products, cart, orders), integrations with 1С/warehouses/payment gateways. Use Laravel 11 with Repository pattern, queues for async operations.
3. Frontend and Checkout. Set up React 18 / Next.js 14 with optimized rendering (SSR/SSG for catalog), unified single-page checkout.
4. Testing. Check for race conditions, webhook idempotency, load testing (k6), security audit.
5. Deploy and Monitoring. Deploy on Vercel / Docker / dedicated server, connect Sentry and Uptime.

SEO for E-commerce

Canonical and Duplication. Faceted filtering generates thousands of URLs (?color=red&size=M&sort=price). Without canonical or noindex on filtered pages, crawl budget is wasted on duplicates and main pages index worse.

Structured data. Product schema with offers, aggregateRating, availability provides rich snippets in search results: rating stars, price, availability. Boosts CTR.

Core Web Vitals on product pages. The hero image is often the LCP element. Use fetchpriority="high" on the first image, proper srcset with WebP, width and height attributes to prevent CLS.

What You Get After Completion

Upon project completion, you receive:

• Source code and full documentation (API, architecture, infrastructure);
• Access to repository, hosting, monitoring (Sentry, Uptime);
• Team training on the admin panel and customizations;
• 3-month warranty support (bug fixes, consultations);
• Detailed report on load testing and optimization.

Timeline Estimates

Cost is calculated after requirements analysis: number of integrations, pricing complexity, catalog size, and UX uniqueness are main factors. Get a free estimate — book a consultation.

Pre-Launch Checklist

• Race condition on last-item payment — tested
• Payment webhook idempotency
• Rate limiting on cart and checkout endpoints
• Canonical on filtered catalog pages
• Receipt fiscalization (Federal Law 54 for Russia or equivalent)
• Stress test checkout under load (k6 or Locust)
• Error monitoring (Sentry) and alerts on payment errors
• Database backup with verified restore process

We guarantee every project passes this checklist before release. Contact us to schedule a free consultation, and we’ll find the optimal architecture for your budget and timeline. Request an estimate for your e-commerce project today.