Skip to main content

​
Overview

Defect Generation synthesizes realistic physical defects (scratches, dents, tears, stains, weld flaws, wrinkles) directly onto defect-free (OK) product photos. For every generated image, the platform automatically computes the pixel-level difference against the untouched OK source image, blends the defect seamlessly into the part’s native surface grain, and exports COCO segmentation masks and 2D bounding boxes (annotations_coco.json).

​
Key Concepts: Presets & Templates

  • Preset: Defines one defect type—its COCO class name, visual description and placement, optional reference close-up photos, and blending mode. You can configure up to 8 presets per template (up to 5 in Combined mode).
  • Template: Saves a collection of presets to your project so you and your team can reload the exact same defect suite across future datasets without re-entering descriptions.

​
Step-by-Step Guide

1

1. Defect-Free (OK) Images — Select Source Photos

In Card 1, choose your defect-free (OK) base images:
  • Dataset tab: Pick an uploaded dataset of OK part photos and select the specific images (or the entire dataset) you want to augment.
  • Upload tab: Upload a single OK part image for quick testing and preset tuning.
2

2. Defect Templates & Presets — Configure Defects

In Card 2 (Defect templates), load an existing project template from the Template Bar or create presets from scratch (click + New):
  • Defect Class: A short label used as the exported COCO category name (e.g., scratch, dent, wrinkle, tear). Presets that share the same Defect Class name automatically share the same COCO category_id in the exported dataset.
  • Defect Description & Placement: One unified text box describing what the defect looks like (type, shape, depth, edges, color, contrast), how big it is (e.g., fraction of the part or cm/mm), and where to place it (using visible part landmarks). If you omit a location, the AI planner automatically selects a valid placement region on the part at random for each image.
  • Randomized Choice Groups: You can vary appearance or placement across a batch within a single preset using flat curly-brace choices such as a {shallow hairline scratch | deep gouge}, about {2% | 5%} of the part's length.
  • Reference Defect Images (Optional, up to 3): Upload or select up to 3 close-up photos of a real defect. The model extracts the defect’s shape and texture from the references without copying the reference photo’s background color, lighting, or position.
3

3. Generation Mode & Advanced Options

Configure how multiple presets are applied:
  • Separate Mode (Default): Generates 1 output image per preset for each selected OK image (N images × P presets = N × P tasks). Best for building balanced single-defect training sets.
  • Combined Mode: Stacks all presets sequentially onto each OK image (N images = N tasks, up to 5 presets). Best for multi-defect inspection scenarios.
  • Faithful Paste vs. Direct Replace: Faithful Paste (Default ON) pastes only the ΔE-gated, low-pass change so the original photo’s sensor grain and micro-texture show through. Direct Replace (OFF) replaces the defect patch directly with generated pixels (useful when the defect shifts seams or stitching).
  • Negative Decoy Paste (Optional, Default OFF): Pastes one unlabeled defect-free patch on a non-overlapping spot using the same blend edge. Keep OFF when training with OK images or low-contrast defects; enable only when training without OK images to suppress boundary false positives.
4

4. Summary, Credits & Launch

In Card 3 (Summary):
  1. Review the total task count and Required credits (1 credit per task).
  2. Verify the Evaluation Rubric Set (defaults to default_defect_generation).
  3. Click Augment to start generation.

​
Writing Effective Defect Prompts

​
Output Dataset & COCO Export Structure

When a Defect Generation job completes, its output dataset in the Data Library includes:
  • rgb_out/: The synthesized defective part images (NOK).
  • rgb_raw/: The original defect-free source images (OK).
  • instances/ & semantics_rgb/: Pixel-accurate defect masks derived from the OK-vs-NOK difference.
  • annotations_coco.json: Ready-to-train COCO annotations containing images, categories (mapped from your Defect Class names), and annotations (bbox, segmentation polygons, and area).