A Semi-Automated Framework for 3D Reconstruction of Medieval Manuscript Miniatures

arXiv cs.CV / 4/13/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes a semi-automated pipeline to convert 2D images of medieval manuscript miniatures into 3D models intended for XR, tactile 3D printing, and web visualization.
It benchmarks seven image-to-3D approaches on 69 figures using both rendering-based metrics and volumetric measures, finding a trade-off between volumetric expansion and geometric fidelity.
Hi3DGen is identified as a strong initial method because its normal-bridging strategy produces a favorable balance of topological quality and surface detail, supporting subsequent expert refinement.
The end-to-end workflow combines SAM-based segmentation, Hi3DGen mesh generation, ZBrush expert refinement, and AI-assisted texturing.
Case studies on Gothic illuminations and Renaissance miniatures demonstrate cross-tradition applicability and produce models that can support WebXR/AR overlays and accessibility-focused tactile prints.

Abstract

This paper presents a semi-automated framework for transforming two-dimensional miniatures from medieval manuscripts into three-dimensional digital models suitable for extended reality (XR), tactile 3D~printing, and web-based visualization. We evaluate seven image-to-3D methods (TripoSR, SF3D, SPAR3D, TRELLIS, Wonder3D, SAM~3D, Hi3DGen) on 69~manuscript figures from two collections using rendering-based metrics (Silhouette IoU, LPIPS, CLIP~Score) and volumetric measures (Depth Range Ratio, watertight percentage), revealing a trade-off between volumetric expansion and geometric fidelity. Hi3DGen balances topological quality with rich surface detail through its normal bridging approach, making it a good starting point for expert refinement. Our pipeline combines SAM segmentation, Hi3DGen mesh generation, expert refinement in ZBrush, and AI-assisted texturing. Two case studies on Gothic illuminations from the Decretum Gratiani (Vatican Library) and Renaissance miniatures by Giulio Clovio demonstrate applicability across artistic traditions. The resulting models can support WebXR visualization, AR overlay on physical manuscripts, and tactile 3D~prints for visually impaired users.