Actions

Download Analytics Citations

Export to: EndNote  |  Zotero  |  Mendeley

Collections

This file is not currently in any collections.

Mask Describable Textures Dataset for Artworks : MDTD-Art [dataset] Open Access

MDTD-Art is a synthetic artwork-degradation dataset designed to model semantically complex damage through semi-transparent texture overlays. It applies 47 texture classes derived from the Describable Textures Dataset to clean artwork images using controllable alpha masks, allowing degradation type and severity to be varied independently. The resulting samples approximate irregular damage patterns such as cracks, stains, fading and material loss across low, medium and high opacity levels. MDTD-Art provides a scalable and controlled resource for studying restoration under partially retained image information and texture-corruption conditions not covered by conventional degradation benchmarks.

Descriptions

Resource type

Dataset

Contributors

Creator: Shum, Hubert P. H. ¹
Editor: Shum, Hubert P. H. ¹

¹ Durham University, UK

Funder

Research methods

MDTD-Art is used to benchmark image restoration and image editing models under controlled texture-overlay degradations. Clean artwork images are paired with semi-transparent texture masks at low, medium and high opacity levels, producing degraded inputs with corresponding clean ground truths. This enables systematic comparison of model performance across degradation severities using full-reference image quality metrics, including L1, PSNR, SSIM and LPIPS, while also supporting analysis of prompt sensitivity, reconstruction fidelity and failure modes such as hallucination and identity drift.

Other description

750 images in PNG format.

Keyword

Subject

Computer vision
Artificial intelligence
Image processing
AI art

Location

Language

Cited in

Identifier

ark:/32150/r1gh93gz625
doi:10.15128/r1gh93gz625

Rights

Creative Commons Attribution 4.0 International (CC BY)

Publisher

Durham University

Date Created

File Details

Depositor

P. Shum

Date Uploaded

29 July 2026, 15:07:40

Date Modified

31 July 2026, 14:07:47

Audit Status

Audits have not yet been run on this file.

Characterization

File format: zip (ZIP Format)

Mime type: application/zip

File size: 253196437

Last modified: 2026:07:29 16:44:08+01:00

Filename: MDTD-ArtIR-r18049g517p-version1.zip

Original checksum: a89dab23d04419e6f2cce987d305666d