Synthetic aging helps cultural heritage image searches with few old photos

Compensating for Scarce Historical Images in Cross-Domain Cultural Heritage Retrieval Using Synthetic Aging

Computer Vision and Pattern Recognition

Summary

It can be hard to match old photos of cultural objects with newer photos because the images look very different. The authors studied whether they could create fake old-looking photos from new ones to help computers learn how to link pictures better. They found that while fake old photos can't fully replace real old ones, they do help when only a small number of real old photos are available. This approach works best when there are some real old photos, improving how well the system finds the same object across time.

What this means in practice

  • For museum digital teams: Improve linking of objects in digital collections when few historical photos exist by adding synthetic aged images for training retrieval models.
  • For photo archiving staff: Enhance search accuracy across old and new photos of physical items by supplementing limited old images with artificially aged new photos.

Authors

Marcin Iwanowski, Adam Mazgaj, Ferdynand Gorski, Sabina Szymoniak

Abstract

Cultural heritage collections often contain contemporary and historical visual records of the same physical object. Linking these records is difficult because corresponding images may differ in viewpoint, acquisition conditions, color reproduction, framing, resolution, and degradation, while genuine historical images are frequently scarce. This study investigates whether synthetically aged contemporary images can replace or complement missing historical training data in bidirectional instance-level retrieval. Synthetic old-domain images are generated using degradation-oriented transformations. An EfficientNetV2-M model is evaluated on identity-disjoint training, validation, and test sets across three dataset partitions and three training seeds. Mixed real-synthetic training is compared with real-only baselines using proportionally scaled and fixed 300-batch-per-epoch schedules. Complete replacement of genuine historical images reduced bidirectional mean R@1 from 86.56% to 81.27%, showing that synthetic aging does not reproduce the full genuine old-domain variability. Increasing the number of independently generated synthetic variants provided no consistent improvement. Under controlled scarcity, however, synthetic completion improved mean R@1 by 3.69 percentage points at 25% genuine historical coverage and by 2.92 points at 50%, relative to the proportionally scaled real-only baselines. At 75%, the gain decreased to 2.00 points, while performance remained comparable to the complete-real-data reference. Fixed-schedule real-only controls did not reproduce these improvements. The results indicate that genuine and synthetic observations are complementary. Synthetic completion primarily benefits retrieval by extending cross-domain identity coverage rather than by increasing training exposure, with its contribution gradually decreasing as genuine historical coverage increases.