Kaputt 2

Retail Track Dataset for the VAND 4.0 Challenge

Challenge Dataset Download Kaputt(1) Paper & Dataset

About Kaputt 2

Kaputt 2 is the next iteration of the Kaputt large-scale visual defect detection dataset, designed specifically for the Retail Track of the VAND 4.0 Challenge at CVPR 2026. To learn more about the original Kaputt dataset, the underlying research, and the paper, please visit the main Kaputt website.

The VAND 4.0 Challenge

The Visual Anomaly and Novelty Detection (VAND) 4th Edition workshop challenge at CVPR 2026 aims to showcase current progress in anomaly detection across practical settings while addressing critical issues in the field. Despite promising results from previous years, there remains significant room for improvement in developing robust and generalizable anomaly detection models for industrial use cases.

The challenge hosts two individual tracks:

  • Retail Track: Kaputt 2 this dataset
  • Industrial Track: MVTec AD 2

Participants can choose a single track or enter both with separate submissions. Key outcomes and winners will be presented at the VAND 4.0 Workshop.

Challenge Website ↗ VAND 4.0 Workshop ↗

The Kaputt 2 Dataset

Kaputt 2 dataset samples
Sample images from the Kaputt 2 dataset (placeholder – final teaser coming soon)

Building on the original Kaputt benchmark, Kaputt2 extends the challenge of visual defect detection in retail logistics. The dataset captures the diversity and variability of object pose and appearance that makes anomaly detection in real-world retail settings particularly challenging. State-of-the-art methods that achieve near-perfect scores on existing benchmarks still struggle significantly in this setting.

Kaputt2 is the official dataset for the Retail Track of the VAND 4.0 Challenge. Kaputt2 is a pure test dataset and does not come with any ground truth defect labels. Participants will create AI models to predict solutions to visual defect/anomaly detection problems as presented through this dataset.

Dataset Download

Please fill out the following form to obtain access to the Kaputt 2 dataset. Once completed, you will receive detailed information on how to download the dataset.

Terms of Use – Kaputt 2 Defect Dataset (K2DD)

These terms govern your use of this Kaputt 2 Defect Dataset ("K2DD").

  1. You acknowledge and agree that the K2DD is subject to the Creative Commons (CC BY-NC-ND 4.0) license. Where the following terms and conditions (the "Superseding terms") conflict with the Creative Commons (CC BY-NC-ND 4.0) license, the Superseding Terms take precedence.
  2. You agree to use this K2DD solely for education and scientific research in the field of computer vision (the "Authorized Purpose").
  3. Amazon is providing the K2DD free of charge, on an "as is" basis, and solely for the Authorized Purpose. Amazon makes no representations or warranties of any kind, express or implied, with respect to this K2DD, including as to third-party approval, endorsement, or non-infringement.
  4. You expressly agree that your use of this K2DD is at your sole risk.
  5. If you are accessing or using this K2DD on behalf of or for the benefit of an entity or institution, you represent and warrant that you are authorized to access these Terms on the entity or institution's behalf.
  6. This K2DD may include images that incorporate third-party intellectual property.
    1. You are solely responsible for determining if your use of third-party intellectual property contained in this K2DD is fair, nominative, or otherwise lawful. Amazon makes no representations in this regard. You agree to seek independent legal advice on this issue as appropriate.
    2. You acknowledge and agree that the presence of third-party intellectual property in this K2DD does not imply approval or endorsement by the intellectual property owner(s), or a representation that this intellectual property is available for lawful use.
    3. You agree not to use this K2DD in a manner that is likely to cause confusion or otherwise infringes third-party intellectual property.
  7. You agree not to remove these Terms from this K2DD.
  8. Any dispute or claim relating to your use of this K2DD will be adjudicated in the state or Federal courts in King County, Washington, and you consent to exclusive jurisdiction and venue in these courts.
  9. You agree to indemnify Amazon, its affiliates, agents, servants, officers, directors and employees, from and against all claims, causes of action, liabilities, suits, administrative actions, damages, costs, or expenses (including reasonable attorneys' fees), whether involving a third-party claim or a direct claim between you and Amazon, that arises from or is related in any way to your use of this K2DD.
  10. To the full extent permissible by law, Amazon disclaims all warranties, express or implied, including, but not limited to, implied warranties of merchantability and fitness for a particular purpose.
  11. To the full extent permissible by law, Amazon will not be liable for any damages of any kind arising from your use of this K2DD, including, but not limited to direct, indirect, incidental, or punitive damages.
  12. By accepting these terms of use, you confirm that you are at least eighteen (18) years of age or older.
By submitting this form, you acknowledge that you have read our Privacy Notice.

Kaputt (original dataset) · VAND 4.0 Challenge · CVPR 2026

✅ Dataset Download Request Submitted Successfully!

You will shortly receive an email with detailed instructions as to how to access the dataset. Please also make sure to check your spam folder.

For any questions or concerns, please contact us at @amazon.com providing your submission ID.

🔒 Security Verification

Please complete the CAPTCHA below to continue