A recipe for every need
Multiple polishing recipes can be set up for different phone models, scratch conditions and the grade you are aiming for. Light marks and heavier scratches each get the treatment that fits.
Scratch removal & cosmetic grading for pre-owned phones
Remove the scratches. Raise the grade.
XTR makes used smartphones worth more. Our polishing system removes display scratches and puts the factory coating back. Our vision system grades every device automatically. Use either one on its own, or run both as a single line.
- US & Korean patents
- Designed & built in the USA
- Since 2012
Solution 01 · stands alone
Polishing Solution
Remove display scratches and restore the coating on fully assembled phones.
Display scratch removal → Solution 02 · stands aloneVision Solution
Grade every device automatically, to grading rules you define.
Automated cosmetic grading → Solution 03 · both togetherComplete Line
Vision, polishing and shop-floor software working as one grade-upgrade line.
Grade, upgrade, track →Polishing Solution · Display scratch removal & grade upgrade
Scratches out. Coating back on. Grade up.
A two-part system for fully assembled phones. First it polishes the scratches out of the display glass. Then it puts back the anti-fingerprint coating that polishing removes, so the screen looks and feels like new. No disassembly.
Patented pressure and time control
Our patented technology (US and Korea) applies the right pressure for the right amount of time. Scratches come out without harming the assembled smartphone.
Coating that meets industry requirements
Plasma preparation, coating and baking restore the anti-fingerprint finish to the standard that certified pre-owned programs expect.
Minimal water, no sealing
The process uses very little water, so phones do not need to be sealed, taped or fixed in protective jigs before polishing.
What a grade upgrade looks like
Drag the handle to compare the display before and after polishing.
Before · C
After · A
Before · C
After · B
Real captures from an XTR vision station. Results depend on the depth of the scratches and the condition of the device.
The equipment
Designed and built by XTR.
PatentedPolish
Auto-Polishing Machine
Removes scratches from several phones at once, each with its own recipe.
Plasma clean
Plasma Unit
Cleans and prepares the glass so the coating bonds.
Coat
Coating Machine
Applies the anti-fingerprint coating to the assembled phone.
Bake
Baking Chamber
Cures the coating into a durable finish.
Vision Solution · Automated cosmetic grading
The same grade for the same phone, every time.
Cameras photograph every side of the phone. Software finds and measures each scratch. The grade is then assigned by rules you define, so it no longer depends on who is doing the grading or how long their shift has been.
- 01
Capture
The station photographs the front, back and all four sides automatically.
- 02
Process
Image processing finds each scratch and measures it.
- 03
Grade
Your grading policy turns the measurements into a grade, in under 30 seconds per device.
- 04
Predict
Machine learning predicts what polishing would do for this phone, before anyone polishes it.
Real captures from an XTR vision station. Every scratch is outlined, numbered and measured.
Your grading rules, not ours
Different customers and markets grade differently. Set up as many grading policies as you need, and grade the same device against any of them without scanning it again.
Grade C
The industry-standard CTIA grading scale, used as the common baseline.
Example for illustration, using the device shown here. Policy names and rules are yours to define.
ML prediction
Know the result before you polish.
8 scratches scored4 likely to clearPredicted C → B · polish
Not every scratch can be polished out, and polishing a phone that will not improve wastes machine time. XTR's machine-learning model looks at every scratch the vision system measured and predicts how likely it is to clear. From that it predicts the grade the phone would reach after polishing.
PolishA better grade is predicted
ReviewToo close to call, so the operator decides
SkipNo gain is predicted, so it moves on as it is
- A clear recommendation. Operators see the predicted grade and what to do, not a wall of data.
- It keeps learning. Every polished phone is scanned before and after, so the model is checked against real results and improves over time.
- Works with your grading policy. The predicted grade is worked out under the same rules you grade with.
Two ways to use it
A standalone grading station
Place it at receiving, trade-in or quality control. Every device gets a consistent, documented grade with the images to back it up.
The brain of the grade-upgrade line
The same measurements predict which phones will improve with polishing, and by how much. Operators get a clear recommendation before any machine time is spent, and a second scan afterwards confirms the result.
Complete Line · Vision + Polishing + Shop-floor software
Grade it. Upgrade it. Track it.
Put the two solutions together and add XTR Shopfloor software, and you have one connected line. Each phone is graded, polished only if it will pay off, re-coated, checked again and tracked the whole way through.
- VisionGrade
Scan and grade the device
- VisionDecide
Will polishing raise the grade?
- PolishingPolish
Remove the scratches
- PolishingRe-coat
Plasma, coating, baking
- VisionVerify
Scan again, confirm the new grade
XTR Shopfloor softwaretracks every device at every step
XTR Shopfloor software
Know where every phone is, and what happened to it.
XTR Shopfloor is the software the whole line reports into. Every phone is tracked from receiving to shipping, every machine posts its own results, and every report comes from that one record. Choose a screen to see what it does.
One screen the whole floor can read from the aisle.
- Pipeline at a glance. Awaiting and done-today counts for every gate, with the stage that is backing up flagged in red.
- Throughput against goal. Ten working days of shipped units, coloured by whether each day hit its target.
- Every result as it lands. A live feed of final-vision outcomes: triage grade, final grade, upgraded or not.
- Built for a wall screen. Auto-refreshing, full-screen and legible from thirty feet.
Customer name and device IMEIs masked.
See the after before you polish.
- Current and predicted, side by side. The pre-polish capture with each scratch scored, next to the surface the model expects after polishing, showing only the defects it predicts will remain.
- Scenarios, not guesses. Each recipe shows its target grade, machine time, pressure and chance of reaching it.
- The money, in order. Sell-as-is value, resale at the target grade, uplift, labour and expected profit, then one recommendation.
Device IMEI and operator name masked. Prices on this screen are sample values.
Yield you can observe, not assert.
- Paired devices. The latest before scan against the latest after scan for every improvable unit.
- Flow of outcomes. Each band is proportional to device count: green for upgrades, grey for no change, red for downgrades.
- Filter to the question. By project, equipment, model and date range, then export to CSV.
Report shown across all projects for one 30-day window.
The model grades itself against reality.
- Three answers per device. The before grade, the ML-predicted after grade and the actual after grade, on the same policy scale.
- Scored in the open. ML triage and machine triage each get a confusion matrix against the real outcome.
- Versioned models. Every prediction records the model version, its test accuracy and the matched pairs it was trained on.
Device IMEIs masked.
CTIA 5.0 is the floor.
- Named standards. Levels, depth rules and per-zone count thresholds: one complete policy per customer.
- Zones weighted by what buyers see. The main display is graded far harder than the enclosure.
- Re-grade without re-scanning. The defect set is stored, so any unit can be graded under a different policy.
Bottlenecks surface themselves.
- Per-step queues. Pending counts, median and P90 dwell for every gate.
- Measured, not argued. The slow gate is flagged from an open-visit ledger.
- Machines are locations. Each polisher is a routable buffer with its own queue.
Every question, one ledger underneath.
- Yield, reject rate, cycle time, throughput. By stage, operator, model and project.
- Grading calibration. Golden units check the policy against expert-graded devices.
- CSV and PDF out of every report. The invoice comes out of the same numbers.
Seven gates, one ledger
Out-of-sequence moves are refused; a supervisor override needs a written reason.
Reason codes, always
No rework or scrap decision is recordable without a base code.
Role-gated stations
A polishing badge cannot record a QC decision. Every action carries an operator.
Customer-facing by design
Customers log in to the same data, scoped to their organisation, with cost per device.
Why XTR
Built to fix what conventional polishing gets wrong.
Most refurbishment lines still polish by feel: wet, slow to prepare, graded by eye and managed on spreadsheets. XTR replaced each weak link with an engineered, measured one.
01
Preparation & water
Conventional polishing
Hours of prep to keep water out
Heavy use of water means every phone has to be sealed, taped and protected first. Water damage still happens.
With XTR
Minimal water, no sealing
The process uses very little water, so there is no sealing, taping or protective jig. Phones go straight from plasma cleaning to polishing.
02
Proof of result
Conventional polishing
No record of what polishing achieved
With no inspection built in, nobody can show what improved or whether the work paid off.
With XTR
Measured before and after
Every phone is scanned before polishing and again after, so each one has a before-and-after record.
03
The decision to polish
Conventional polishing
A judgement call, no cost picture
Whether to polish is decided by eye at the bench, and varies by person and by shift.
With XTR
Predicted first, then decided
The system predicts the grade after polishing and weighs the gain against the cost. Operators get a clear recommendation.
04
Flow & inventory
Conventional polishing
Spreadsheets and whiteboards
Phones go missing between stations and bottlenecks are found late.
With XTR
Software built for the floor
XTR Shopfloor tracks every phone through every step and shows queues and inventory live.
05
Polishing recipe
Conventional polishing
One setting for every phone
Light marks get over-worked, deep scratches under-worked, and results depend on the operator.
With XTR
A recipe matched to the phone
Recipes are chosen for the phone's condition and the target grade, and the machine records what it did.
06
Grading
Conventional polishing
Inconsistent, one-size-fits-all
Grading by eye differs between people and sites, and one fixed standard cannot serve every market.
With XTR
Objective, with a policy per customer
Grades come from measurements and your own grading policies, one for each customer or market.
Company
Born on a repair floor.
XTR was founded in 2012 inside a phone repair center, where it developed the polishing processes that became its patented technology. Today it serves carriers, insurers and refurbishers running certified pre-owned programs.
- US & Korean patentsPolishing technology
- Made in USAMachines designed and built in-house
- CPO-readyFinish and records that programs require
- 2012
Founded inside a repair center; polishing processes developed.
- 2020
Korean patent awarded.
- 2022
US patent awarded.
- 2025
Vision grading launched.
- Now
One complete line: vision, polishing and shop-floor software.
Contact
See what it would do for your devices.
Tell us which solution you are interested in and roughly how many devices you handle. We will show you the equipment and what it could change for your grade mix.
Or write to info@xtrtechnologies.com