Real-time primitive extraction
Convert raw point clouds into parametric primitives with pose and dimensions, enabling measurement and downstream automation.
ROBUST • REAL-TIME • AUTOMATION
Real-time geometry recognition and measurement
from point clouds.
CurvSurf develops and distributes real-time 3D object/geometry recognition, measurement, and extraction SDK for 3D imaging/measurement applications for tablets, mobile and 3D scanning devices.
OUR TECHNOLOGY
FindSurface, using innovative geometric abstract based algorithm, can handle 3D image processing in dynamic real world environment with significantly faster speed.
Robust to real-world scans
Designed for unordered, partial, and outlier-heavy data often seen in mobile capture and field scanning.
SDK-first integration
Lightweight and easy to embed, enabling both on-device deployment and cloud-based services depending on your needs.
By using FindSurface, users can rapidly develop solutions for automated 3D geometry recognition, measurement and tracking applications. Its fully automated object detection and parameter estimation software can create clear images with accurate dimensional measurements instantly from large volume of image data in unordered, incomplete and error-contaminated point cloud. Our solution enables point cloud data from Cameras, UAV, Satellite, Aerial & Industrial Scanners, Robots and Handheld devices to automatically extract 2D/3D primitives in real time.
This is a revolutionary technology that can be extended to a robust perception technology for pre-defined object identification and localization with “human-like” robustness.
Supported geometric features are Cuboid, Plane, Sphere, Cylinder, Cone, and Torus with geometric parameters such as 3D position, Orientation, Size, Radius, etc. Applications include Spatial Computing, Physical AI, Reverse Engineering, AR (Augmented Reality), Robot Vision, Logistic Managements, Deep Learning, Collision Avoidance, UAV, Autonomous Car, and any 3D object recognition applications which needs “Human-Like” robust perception.
The core architecture consists of three algorithmic modules, allowing for object identification, point segmentation, and model fitting. Orthogonal distance fitting (ODF) algorithms estimate the model parameters by minimizing the sum of the squares of the minimum distances between the model feature and the measurement points. Curvature analysis of the local quadratic surfaces fitted to small patches of point cloud provide the necessary seed information for automatic model selection, point segmentation, and model fitting.
ABOUT US
SUNG JOON AHN, PH.D
CEO / Founder
With more than 20 years of critical technical roles and R&D experience, Dr. Ahn founded CurvSurf in 2013. He worked as a junior research scientist at the LG Electronics R&D center from 1987 to 1990. From 1990, he worked as a research scientist for the Fraunhofer Institute for Manufacturing Engineering and Automation (IPA) in Stuttgart, Germany and recived his Ph.D. in 2004. From 2005 to 2013, he worked for Sungkyunkwan University in South Korea. Dr. Ahn has made remarkable breakthroughs in pattern recognition, optical 3D-measurement, close-range photogrammetry, camera calibration, and 3D-information processing.
JINGYU CHOI
CTO
He started his career as a “human factor” and “3D data processing” research engineer with KETI (Korea Electronics Technology Institute) in 2010. Working under the R&D center senior members, he developed a Gesture Recognition solution by using a vision system. Utilizing his academic and professional knowledge, he dedicated 4 years with DigiCAP Co. Ltd. While working in the capacity of Mobile Solution Development Engineer (MSDE). He graduated from Sungkyungkwan University, where he received his BS (2009) in computer engineering and Master (2011) in electronic-electrical-computer engineering. He is currently working as the CTO with CurvSurf.
SUNG-GOO KIM
Principal Engineer
He is the principal engineer at CurvSurf, specializing in prototype and demo development for real-time 3D experiences across mobile and XR platforms. He earned his B.S. in Computer Engineering from Sungkyunkwan University (2014) and pursued graduate-level studies in computer graphics, building a strong foundation in C/C++ and OpenGL. He develops end-to-end interactive demos for iOS (iPhone/iPad), visionOS (Apple Vision Pro), and Android devices, including Galaxy XR, using Swift/SwiftUI, Metal, ARKit, C/C++, and Kotlin.