Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration

2026-07-01

AI Summary

This work addresses the limitations of existing 3D inpainting methods, which predominantly focus on geometric completion while neglecting texture recovery and struggling with complex objects. To overcome these challenges, we propose the first end-to-end framework that jointly reconstructs both shape and texture of damaged objects from multi-view images. Our approach leverages automatically synthesized damaged-complete data pairs, a Mask Self-Perceiver module, and a Depth-Aware Mask Rectifier, integrated within a coarse-to-fine 3D mesh reconstruction strategy. This enables high-resolution, semantically consistent, and view-coherent inpainting results. Extensive evaluations on both synthetic and real-world benchmarks demonstrate that our method significantly outperforms state-of-the-art techniques in multi-view image inpainting and textured 3D reconstruction.

Abstract

Restoring incomplete or damaged 3D objects is crucial for cultural heritage preservation, occluded object reconstruction, and artistic design. Existing methods primarily focus on geometric completion, often neglecting texture restoration and struggling with relatively complex and diverse objects. We introduce Restore3D, a novel framework that simultaneously restores both the shape and texture of broken objects using multi-view images. To address limited training data, we develop an automated data generation pipeline that synthesizes paired incomplete-complete samples from large-scale 3D datasets. Central to Restore3D is a multi-view model, enhanced by a carefully designed Mask Self-Perceiver module with a Depth-Aware Mask Rectifier. The rectified masks learned by the self-perceiver guide an image integration and enhancement phase, helping retain observed shape and texture patterns while refining the generated regions and mitigating the low-resolution limitations of the base model, yielding high-resolution, semantically coherent, and view-consistent multi-view images. A coarse-to-fine reconstruction strategy is then employed to recover detailed textured 3D meshes from refined multi-view images. Experiments on synthetic and real broken-object benchmarks show that Restore3D improves multi-view restoration quality and textured-mesh reconstruction over representative inpainting, completion, and reconstruction baselines in the evaluated settings. Project Page: restore3dx.github.io

Problem

• 3D object restoration
• shape completion
• texture restoration
• multi-view reconstruction
• broken objects

Innovation

• shape and texture restoration
• multi-view 3D reconstruction
• Mask Self-Perceiver
• Depth-Aware Mask Rectifier
• coarse-to-fine reconstruction