Inspection AX›PBS

PBS

Physically-Based Synthesis · Physics-Based Synthetic Data

Physically-based synthesis (PBS) simulates the interaction of light and matter to generate realistic defect training data, not the probabilistic images of generative AI.

A real captured image compared with a PBS synthetic image
REALPBS

PBS

The barrier to putting inspection AI on the line:
not enough training data

More and more battery, electronic component and auto parts lines are bringing AI into visual and X-ray inspection.
But once a trained model goes onto a real line, it hits the data barrier first, regardless of how good the algorithm is.

Generative AI vs Physically-Based Synthesis (PBS)

Keep the shape, change only the defects and imaging conditions
to create training data close to real captures

CategoryGenerative AI image generationPhysically-Based Synthesis (PBS)
MethodCreates new scenes from text or example imagesGenerates images reflecting the physical properties of 3D shape, material and lighting
StrengthsHigh creative flexibility for fast, varied stylesSimulates material–light interaction · high physical accuracy and realistic results
LimitationsLacks real physical accuracy · hard to keep 3D geometry consistentRequires manual setup and explicit 3D models
Shape consistencyAdding only a fine defect to the same part requires extra control to keep the shape consistentChanges defects and imaging conditions while keeping the shape

In manufacturing inspection, what matters is changing defects and imaging conditions while keeping the part's shape. SNUAILAB Physically-Based Synthesis is built on PBS that reflects CAD geometry, light and material.

SNUAILAB Physical-Synthetic

From shape and material to defects, lighting and labels,
all generated together

Expands training data for manufacturing inspection AI across diverse defects and imaging conditions.

Process

From CAD input
to automatic label output

  1. 01

    CAD input

    CAD loading
    Part classification · material matching

  2. 02

    Gap compensation

    Compensates CAD-to-part deviation
    and surface roughness

  3. 03

    Optical simulation

    Lighting · camera · lens
    Physically-based rendering

  4. 04

    Defect generation · labeling

    Shape-change defect generation
    Automatic label output

From a single CAD model, it generates large volumes of consistent training data while changing viewing angles and conditions.

PBS

Photorealistic defect images
with consistent, accurate labels

Core Technology

Photorealistic defect data generation
that physically reproduces lighting, camera and material

Examples · CAD-to-Part Gap Compensation

Closing the gap between CAD and the real product
for more realistic synthetic images

A CAD file is an idealized model that does not reflect the real part's material properties, machining deviations or deformation. PBS detects and compensates the gaps that affect imaging, such as rounding, machining deviation and assembly deviation.

Original CAD — sharp edges and flat ends
Original CAD — sharp edges and flat ends
After edge rounding — shape and reflections that follow the edge curvature
After edge rounding — shape and reflections that follow the edge curvature
Surface roughness applied — light reflection and surface detail by material
Surface roughness applied — light reflection and surface detail by material

Generation Examples · Defect Shapes and Viewing Angles

Data generated with varied
defect shapes and viewing angles

Creates defects by modifying the product's 3D shape and renders synthetic images from various viewing angles.

Global shape change + mesh-based local defect
Global shape change + mesh-based local defect
PBS images from multiple angles
PBS images from multiple angles
Global shape-change sample — top protrusion at different tilt angles
Global shape-change sample — top protrusion at different tilt angles

Examples · PBS-Based 3D Damaged Surfaces

Applying material effects
to generate realistic damaged surfaces

Both the shape and the surface texture of the damaged area are rendered.

Damaged surface generated with PBS
Damaged surface generated with PBS
ZOOM — shape and surface texture of the damage
ZOOM — shape and surface texture of the damage

Realistic damage images are generated and used as defect training data for manufacturing inspection AI.

When to Use

When you need PBS

Best suited for: lines where NG samples are rare or inspection items change often

Short on defect samples?
Start with SNUAILAB PBS

Maximize your business values
by adopting industry-specific AI solutions.

Inquiry