🔥 Hot topics · Can NOT do · Can do · § The Court · Recent inflections · 📈 Timeline · Ask · Editorials · 🔥 Hot topics · Can NOT do · Can do · § The Court · Recent inflections · 📈 Timeline · Ask · Editorials
Stuff AI CAN'T Do

Can AI determine the perfect clothing sizes from a series of photos ?

What do you think?

What would it take for an AI to pick “the perfect” clothing size straight from a photo? Today’s systems can measure basic body dimensions with moderate accuracy, but translating those numbers into a size that also feels right—with the right drape and fit rules—remains an open challenge. Let’s separate what’s possible today from what’s still out of reach.

Background

Current AI systems estimate basic body measurements from single photos using 2D pose estimation and anthropometric models to infer height, bust, waist, and hip dimensions, achieving typical errors of ±2–3 cm in controlled settings (SOURCE: McKinsey & Company — https://www.mckinsey.com/industries/retail/our-insights/notes-from-the-ai-frontier-modeling-the-impact-of-ai-on-the-world-economy). More advanced pipelines combine multiple views or short videos to reduce occlusion and improve volumetric reconstruction, yet they still output static measurements rather than a curated size recommendation (SOURCE: McKinsey & Company). Fully automated “perfect fit” determination remains out of reach because it requires real-time integration of material properties, user feedback, and retailer-specific grading standards (SOURCE: McKinsey & Company).

AI clothing-size systems also face variability in pose, lighting, and clothing type; accurate estimation often depends on multiple photos from different angles, and results can still be unreliable (SOURCE: IEEE, enriched May 13, 2026).

Status last checked on August 11, 2026.

📰

Gallery

In the Court of AI Capability
Summary of Findings
Verdict over time
May 2026May 2026May 2026May 2026Jun 2026Jun 2026Jun 2026Jun 2026Jun 2026Jun 2026Jul 2026Jul 2026Jul 2026Jul 2026Jul 2026Aug 2026Aug 2026
Sitting at the Bench Filed · Aug 11, 2026
— The Question Before the Court —

Can AI determine the perfect clothing sizes from a series of photos?

★ The Court Finds ★
▼ Downgraded from Almost
No

Beyond AI for now. The capability gap is real.

Ruling of the Bench

After careful deliberation, the jury concluded that today’s AI remains unfit to tailor the perfect fit from pixels alone, finding no system capable of extracting infallible measurements from photographs. The lone vote against stood firm, citing persistent uncertainties in scale, angle, and fabric distortion that even the sharpest algorithms cannot yet iron out. The jury’s ruling: Let the tailor keep the tape measure, for now.

— Hon. J. von Neumann III, Presiding
Jury Tally
0Yes
0Almost
1No
Verdict Confidence
90%
The Court of AI Capability is, of course, not a real court.
But the data is real.
The Case File · Stacked History
Session I · May 2026 In_research
Session II · May 2026 Almost · 78%
Session III · May 2026 Almost · 72%
Session IV · May 2026 Almost · 73%
Session V · Jun 2026 Almost · 79%
Session VI · Jun 2026 Almost · 70%
Session VII · Jun 2026 Almost · 78%
Session VIII · Jun 2026 In_research · 85%
Session IX · Jun 2026 Almost · 85%
Session X · Jun 2026 Almost · 83%
Session XI · Jul 2026 Almost · 85%
Session XII · Jul 2026 Almost · 85%
Session XIII · Jul 2026 Almost · 85%
Session XIV · Jul 2026 Almost · 80%
Session XV · Jul 2026 Almost · 80%
Session XVI · Aug 2026 Almost · 80%
Case № 930C · Session XVII
In the Court of AI Capability

The Case File

Docket № 930C · Session XVII · Vol. XVII
I. Particulars of the Case
Question put to the courtCan AI determine the perfect clothing sizes from a series of photos?
SessionXVII (17 hearing)
Convened11 Aug 2026
Previously ruledIN_RESEARCH (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → IN_RESEARCH (Jun '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → ALMOST (Jul '26) → ALMOST (Jul '26) → ALMOST (Jul '26) → ALMOST (Jul '26) → ALMOST (Jul '26) → ALMOST (Aug '26) → NO (Aug '26)
Presiding JudgeHon. J. von Neumann III
II. Cumulative Tally Across Sessions

Across 17 sessions, 39 jurors have heard this case. Combined tally: 2 YES · 33 ALMOST · 4 NO · 0 IN RESEARCH.

Note: cumulative includes older juror opinions. The current session tally above is the live verdict.

III. Verdict

By a vote of 0 — 0 — 1, the panel returns a verdict of NO, with verdict confidence of 90%. The court so orders. Verdict downgraded from prior session.

IV. Statements from the Bench
Juror I NO

"no AI system reliably derives precise body measurements from photos alone"

J. von Neumann III
Presiding Judge
M. Lovelace
Clerk of the Court

What the audience thinks

No 30% · Yes 4% · Maybe 65% 23 votes
No · 30%
Maybe · 65%
41 days of activity

Discussion

no comments

Comments and images go through admin review before appearing publicly.

17 jury checks · most recent 1 day ago
11 Aug 2026 1 juror · cannot cannot
06 Aug 2026 1 juror · undecided undecided
31 Jul 2026 2 jurors · undecided, undecided undecided
26 Jul 2026 1 juror · undecided undecided
15 Jul 2026 1 juror · undecided undecided
10 Jul 2026 3 jurors · undecided, undecided, can undecided
04 Jul 2026 1 juror · undecided undecided
29 Jun 2026 2 jurors · undecided, undecided undecided
24 Jun 2026 2 jurors · undecided, undecided undecided
18 Jun 2026 2 jurors · undecided, cannot undecided
13 Jun 2026 3 jurors · undecided, cannot, undecided undecided
07 Jun 2026 2 jurors · undecided, undecided undecided
02 Jun 2026 5 jurors · undecided, undecided, can, undecided, undecided undecided
28 May 2026 3 jurors · undecided, undecided, undecided undecided
22 May 2026 3 jurors · undecided, undecided, undecided undecided
17 May 2026 3 jurors · cannot, undecided, undecided undecided
13 May 2026 4 jurors · undecided, undecided, undecided, undecided undecided

Each row is a separate jury check. Jurors are AI models (identities kept neutral on purpose). Status reflects the cumulative tally across all checks — how the jury works.

More in Physical

Got one we missed?

Add a statement to the atlas. We review weekly.