ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation

2026-09-10

AI Summary

该研究通过噪声反转和调制，将重建先验注入多视图3D生成中，以完成未观察区域并细化可见几何结构。

Abstract

Qualitative results and an illustration of our core idea. Top left: reconstruction results on benchmark images. Top right: reconstruction results on real-world images. Bottom: illustration of reconstruction-guided noise initialization and modulation. Given multiple input images, we predict a point cloud in canonical space, deterministically inject the predicted geometry into the diffusion process through noise inversion, and modulate the resulting noise to preserve the generative flexibility required to complete unobserved regions and refine visible geometry.

Problem

• reconstruction prior
• multi-view 3D generation
• noise inversion
• modulation
• geometry completion

Innovation

• Reconstruction Prior
• Noise Inversion
• Modulation
• Multi-view 3D Generation