GEAR: Reconstruction of Classical Paintings via Geometry Grounding and Appearance Restitution
2026-07-20 • Multimedia
Multimedia
AI summaryⓘ
The authors introduce a new task called Classical Painting-to-3D (CP3D), which focuses on turning single classical paintings into 3D models that look accurate and believable from different views. They note that traditional methods struggle because paintings have unique styles and weak depth clues compared to photos. To solve this, they propose GeAR, a two-step method that first fixes the painting’s lighting and shape cues, then recovers the original textures and details to maintain the artwork's appearance. They also create a large dataset called HeriArch to test their approach, showing it works better than existing methods in making geometrically correct and visually faithful 3D scenes.
3D reconstructionclassical paintingsgeometry groundingappearance restitutionnovel-view synthesisshading and illumination3D Gaussian reconstructionmulti-view consistencydigital preservationbenchmark dataset
Authors
Qinyu Zhang, Xinda Liu, Yunchen Li, Yunzhuo Liu, Chenxi Hu, Kang Li, Guohua Geng
Abstract
Classical paintings preserve rich spatial, cultural, and historical content, making their reconstruction as explorable 3D scenes valuable for digital preservation, immersive exhibition, and cultural engagement. Yet, unlike photographs, they often depict scenes in a single-view, stylized manner, with weak perspective, lighting, and depth cues. Existing 3D reconstruction methods are largely built on natural-image priors, making it difficult to recover geometrically plausible and visually faithful 3D representations from such inputs. To address this challenge, we introduce Classical Painting-to-3D (CP3D), a new task that aims to recover a 3D representation from a single classical painting while jointly ensuring geometric plausibility, appearance fidelity to the source artwork, and plausible novel-view synthesis. We further propose GeAR, a training-free two-stage framework for Geometry Grounding and Appearance Restitution. GeAR first converts the input painting into a geometry-grounded representation with more coherent shading and illumination cues, improving the stability of 3D Gaussian reconstruction. It then restores artwork-faithful appearance across views under spatial constraints and multi-view consistency, recovering the painterly textures and details weakened during grounding. In addition, we construct HeriArch, a curated benchmark of 10,160 high-resolution classical artworks for systematic evaluation of CP3D. Extensive experiments and user studies show that GeAR consistently outperforms strong baselines in geometric plausibility, appearance fidelity, and human preference. Code and dataset will be released publicly.