DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection

• URL: http://arxiv.org/abs/2503.13985v2
• Date: Thu, 27 Mar 2025 05:23:02 GMT
• Title: DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection
• Authors: Jaewoo Song, Daemin Park, Kanghyun Baek, Sangyub Lee, Jooyoung Choi, Eunji Kim, Sungroh Yoon,
• Abstract summary: DefectFill is a novel method for realistic defect generation that requires only a few reference defect images.<n>It enables precise capture of detailed, localized defect features and their seamless integration into defect-free objects.
• Score: 32.80355689164011
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Developing effective visual inspection models remains challenging due to the scarcity of defect data. While image generation models have been used to synthesize defect images, producing highly realistic defects remains difficult. We propose DefectFill, a novel method for realistic defect generation that requires only a few reference defect images. It leverages a fine-tuned inpainting diffusion model, optimized with our custom loss functions incorporating defect, object, and attention terms. It enables precise capture of detailed, localized defect features and their seamless integration into defect-free objects. Additionally, our Low-Fidelity Selection method further enhances the defect sample quality. Experiments show that DefectFill generates high-quality defect images, enabling visual inspection models to achieve state-of-the-art performance on the MVTec AD dataset.

Related papers

• Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models [58.98742597810023]
  Vision models have to behave in a robust way to disturbances such as noise or blur. This paper studies two datasets of blur corruptions, which we denote OpticsBench and LensCorruptions. Evaluations for image classification and object detection on ImageNet and MSCOCO show that for a variety of different pre-trained models, the performance on OpticsBench and LensCorruptions varies significantly.
  arXiv  Detail & Related papers  (2025-04-25T17:23:47Z)
• DiffDoctor: Diagnosing Image Diffusion Models Before Treating [57.82359018425674]
  We propose DiffDoctor, a two-stage pipeline to assist image diffusion models in generating fewer artifacts.<n>We collect a dataset of over 1M flawed synthesized images and set up an efficient human-in-the-loop annotation process.<n>The learned artifact detector is then involved in the second stage to optimize the diffusion model by providing pixel-level feedback.
  arXiv  Detail & Related papers  (2025-01-21T18:56:41Z)
• DefFiller: Mask-Conditioned Diffusion for Salient Steel Surface Defect Generation [1.2362191015139727]
  DefFiller is a mask-conditioned defect generation method that leverages a layout-to-image diffusion model.<n>We show that DefFiller produces high-quality defect images that accurately match the provided mask conditions.
  arXiv  Detail & Related papers  (2024-12-20T05:08:42Z)
• PETALface: Parameter Efficient Transfer Learning for Low-resolution Face Recognition [54.642714288448744]
  PETALface is the first work leveraging the powers of PEFT for low resolution face recognition.<n>We introduce two low-rank adaptation modules to the backbone, with weights adjusted based on the input image quality to account for the difference in quality for the gallery and probe images.<n>Experiments demonstrate that the proposed method outperforms full fine-tuning on low-resolution datasets while preserving performance on high-resolution and mixed-quality datasets.
  arXiv  Detail & Related papers  (2024-12-10T18:59:45Z)
• Few-shot Defect Image Generation based on Consistency Modeling [1.8029094254659288]
  DefectDiffu is a novel text-guided diffusion method to model defect consistency across multiple products. We show that DefectDiffu surpasses state-of-the-art methods in terms of generation quality and diversity.
  arXiv  Detail & Related papers  (2024-08-01T08:29:42Z)
• Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics [27.03052142039447]
  We introduce the Defect Spectrum, a comprehensive benchmark that offers precise, semantic-abundant, and large-scale annotations for a wide range of industrial defects. Building on four key industrial benchmarks, our dataset refines existing annotations and introduces rich semantic details, distinguishing multiple defect types within a single image. We also introduce Defect-Gen, a two-stage diffusion-based generator designed to create high-quality and diverse defective images.
  arXiv  Detail & Related papers  (2023-10-26T11:23:24Z)
• CINFormer: Transformer network with multi-stage CNN feature injection for surface defect segmentation [73.02218479926469]
  We propose a transformer network with multi-stage CNN feature injection for surface defect segmentation. CINFormer presents a simple yet effective feature integration mechanism that injects the multi-level CNN features of the input image into different stages of the transformer network in the encoder. In addition, CINFormer presents a Top-K self-attention module to focus on tokens with more important information about the defects.
  arXiv  Detail & Related papers  (2023-09-22T06:12:02Z)
• Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation [19.018561017953957]
  We propose the first defect image generation method in the challenging few-shot cases. Our method consists of two training stages. First, we train a data-efficient StyleGAN2 on defect-free images as the backbone. Second, we attach defect-aware residual blocks to the backbone, which learn to produce reasonable defect masks.
  arXiv  Detail & Related papers  (2023-03-04T11:43:08Z)
• Exposure Correction Model to Enhance Image Quality [70.7848787073901]
  We propose an end-to-end exposure correction model to handle both under- and overexposure errors. Our model contains an image encoder, consecutive residual blocks, and image decoder to synthesize the corrected image. We show that after applying exposure correction with the proposed model, the portrait matting quality increases significantly.
  arXiv  Detail & Related papers  (2022-04-22T11:38:52Z)
• Improving robustness against common corruptions with frequency biased models [112.65717928060195]
  unseen image corruptions can cause a surprisingly large drop in performance. Image corruption types have different characteristics in the frequency spectrum and would benefit from a targeted type of data augmentation. We propose a new regularization scheme that minimizes the total variation (TV) of convolution feature-maps to increase high-frequency robustness.
  arXiv  Detail & Related papers  (2021-03-30T10:44:50Z)
• Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection [34.699695525216185]
  Defect-GAN is an automated defect synthesis network that generates realistic and diverse defect samples. It learns through defacement and restoration processes, where the defacement generates defects on normal surface images. It can also mimic variations of defects and offer flexible control over the locations and categories of the generated defects.
  arXiv  Detail & Related papers  (2021-03-28T15:53:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.