KOEN
Contact
2026 H2 Innovative IT Award · AI & Data

We generate missing data, and find hidden risks

IPIS Lab synthesises AI training data for rare and hazardous conditions that cannot be captured in the field (DataSynOps), and uses that data to read infrastructure imagery automatically (InfraSafe AI).

SYNTHETIC FRAME · AUTO-LABEL DETECTED 0 / 7
6
Paying clients
2 are repeat buyers
6
Public programs
incl. K-water open innovation
10
Domain pipelines
6 verified in delivery
5
Revenue domains
Defense · Infrastructure · Environment · Manufacturing
3
Granted patents
1 filed · 2 software regs.
Clients
Farm HannongLIG SystemsGERIE&G ConsultantK2 Laser SystemsEPS Solution
Problem

What blocks an AI project is the data, not the model

Models can be downloaded. The training data for your site cannot be bought anywhere.

Rare events, by definition, leave no data

Voids, sinkholes, wildfires, industrial accidents — the very conditions a model must detect are the ones that almost never occur. Field capture alone will never reach training scale.

Collection and labeling consume the budget

Capture, cleaning and manual annotation absorb most of a project's cost and schedule, and the bill arrives again with every new site.

Security and privacy close the door

Defense, medical and site CCTV footage often cannot leave the premises at all, which rules out outsourced annotation before the work begins.

Human reading is not repeatable

Two inspectors mark the same crack differently, and every agency keeps its own criteria. Re-inspection reproduces the variance instead of removing it.

Turn collecting data into generating it, and the bottleneck disappears.
Engine · DataSynOps

Generate exactly the data you need

Physics-based simulation and generative AI synthesise rare conditions at scale, with ground-truth labels attached automatically.

STEP 1

Diagnose the gap

We identify the conditions the current model fails on, automatically.

STEP 2

Synthesise the data

Physics-based simulation combined with generative realism refinement.

STEP 3

Auto-label

SAM2 produces pixel-precise polygons, sorted into three confidence tiers.

STEP 4

Retrain and verify

Synthetic pre-training, field fine-tuning, then measured verification.

STEP 5

Deploy and report

Detections and the evidence behind them are exported as a report.

CLOSED-LOOPSTEP 5 feeds STEP 1
DataSynOps-α
Synthesis engine for video-analytics training data
Certified test report CT24-104451K
DataSynOps-ε
Synthesis engine for image-enhancement training data
Software registration C-2024-054601
DataSynOps v2.0
Low-light synthetic data platform
2026 Innovative IT Award technology
AutoLabel Forge
SAM2-based automatic labeling pipeline
74.4% field recall · 83.6% precision
Track record

Secured as rights, verified by third parties

The core of our generation method is held as granted patents and verified by certified testing and awards.

Intellectual property

  • Method and apparatus for generating training data for AI video analytics modelsKR 10-2687011
  • Integrated image enhancement and training-data generation using a generative recurrent networkKR 10-2654017
  • Image matting method and apparatusKR 10-2624296

Certification

  • 2 certified test reportsIssued by KCL
  • 2 software registrationsKorea Copyright Commission
  • 4 government programsKRW 396M awarded to date

Awards

  • 2026 H2 Innovative IT AwardJoongAng Ilbo
  • 2025 S.Challenge IR Grand Final, Excellence AwardSeoul Regional SMEs Office
  • Selected for Seoul Pavilion, CES 2025SBA
Company

An execution team built on thirty years of imaging research

A founder-led R&D organisation combined with an advisory network of world-class imaging researchers.

Joonki Paik, Ph.D.
FOUNDER & CEO

Professor, Department of Imaging Science, Chung-Ang University. Ph.D. in Electrical Engineering, Northwestern University (1990). Over thirty years in image processing and computer vision, with numerous national R&D programs led as principal investigator for the Ministry of Science and ICT, the Ministry of Food and Drug Safety and the Ministry of Culture, Sports and Tourism. Founded IPIS Lab in 2023 to commercialise the laboratory's technology.

Jinbeum Jang, Ph.D.Principal Researcher · Head of Technology
Ph.D. in Image Engineering, Chung-Ang University (2020). Leads generative AI and defect-detection pipelines
Injae LeeSenior Researcher
Object detection and tracking. Built the SAM2 auto-labeling pipeline
Hyungseok OhResearcher
3D vision and image processing
Minju BaekResearcher
EO-IR image analysis
A. Katsaggelos, Ph.D.Advisor
Joseph Cummings Professor, Northwestern University
M. Abidi, Ph.D.Advisor
Emeritus Professor, University of Tennessee, Knoxville
Yoon KimAdvisor
CSO, President — Twelve Labs
Contact

Tell us what has to be detected on your site

Tell us what has to be detected on your site. We will first assess whether that data can be generated. If you have sample footage, we will prepare an auto-labeling demonstration with it.