Sampling variability ranks reconstruction error in lacquerware image inpainting across models and collections

Abstract Generative inpainting can produce visually persuasive but inaccurate completions of lacquerware photographs. We examined whether variability across three seeded reconstructions predicts the masked error of a fourth, held-out reconstruction under synthetic occlusion. The analysis included 64 original objects, 40 external museum catalogue entries, and two diffusion models. Object-level Pearson correlations between variability and error were 0.7176 and 0.7664 in the original cohort, and 0.9043 and 0.9162 externally. Retaining approximately 40% of the lowest-variability entries reduced the mean masked error of selected outputs in each analysis, although no reconstruction was improved. The incremental advantage over inexpensive image descriptors was uncertain in the original cohort. Subsequent two-expert foreground and material assessment supported the association in restricted external subsets, while anonymous visual ratings showed limited agreement despite adjacent-grade differences. Sampling variability may help prioritize synthetic-loss reconstructions for human review; it does not establish historical authenticity or conservation suitability.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-12
DOI
https://doi.org/10.21203/rs.3.rs-11459219/v1
Primary Topic
Generative Adversarial Networks and Image Synthesis
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Sampling variability ranks reconstruction error in lacquerware image inpainting across models and collections

xiao zhang, peng yue, jia hou
Research Square
Generative Adversarial Networks and Image Synthesis
preprint

Sampling variability ranks reconstruction error in lacquerware image inpainting across models and collections

xiao zhang, peng yue, jia hou
preprint en

Abstract

Abstract Generative inpainting can produce visually persuasive but inaccurate completions of lacquerware photographs. We examined whether variability across three seeded reconstructions predicts the masked error of a fourth, held-out reconstruction under synthetic occlusion. The analysis included 64 original objects, 40 external museum catalogue entries, and two diffusion models. Object-level Pearson correlations between variability and error were 0.7176 and 0.7664 in the original cohort, and 0.9043 and 0.9162 externally. Retaining approximately 40% of the lowest-variability entries reduced the mean masked error of selected outputs in each analysis, although no reconstruction was improved. The incremental advantage over inexpensive image descriptors was uncertain in the original cohort. Subsequent two-expert foreground and material assessment supported the association in restricted external subsets, while anonymous visual ratings showed limited agreement despite adjacent-grade differences. Sampling variability may help prioritize synthetic-loss reconstructions for human review; it does not establish historical authenticity or conservation suitability.

Research Square
Kangwon National University (KR), Christian-Albrechts-Universität zu Kiel (DE), Zhengzhou Business University (CN)
Generative Adversarial Networks and Image Synthesis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon