GeoGS3D：基于几何感知扩散模型与高斯溅射的单视图3D重建
GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting
AI总结：
本研究提出GeoGS3D两阶段框架，结合几何感知扩散模型与高斯溅射实现单视图3D重建，通过正交平面分解、对极注意力及GDS剪枝提升效率与质量，实验验证其多视图一致性与重建效果优异。
摘要：
我们提出了GeoGS3D，这是一种用于从单视图图像重建细节丰富的3D对象的新型两阶段框架。受预训练2D扩散模型成功的启发，我们的方法引入正交平面分解机制，从2D输入中提取3D几何特征，以促进多视图一致图像的生成。在后续的高斯溅射（Gaussian Splatting）阶段，这些图像通过对极注意力进行融合，充分利用视图间的几何相关性。此外，我们提出了一种新的度量标准——高斯散度显著性（GDS），用于在优化过程中剪枝不必要的操作，显著加速重建过程。大量实验表明，GeoGS3D生成的图像具有高视图一致性，且在定性和定量上均能重建出高质量的3D对象。
英文摘要：
We introduce GeoGS3D, a novel two-stage framework for reconstructing detailed 3D objects from single-view images. Inspired by the success of pre-trained 2D diffusion models, our method incorporates an orthogonal plane decomposition mechanism to extract 3D geometric features from the 2D input, facilitating the generation of multi-view consistent images. During the following Gaussian Splatting, these images are fused with epipolar attention, fully utilizing the geometric correlations across views. Moreover, we propose a novel metric, Gaussian Divergence Significance (GDS), to prune unnecessary operations during optimization, significantly accelerating the reconstruction process. Extensive experiments demonstrate that GeoGS3D generates images with high consistency across views and reconstructs high-quality 3D objects, both qualitatively and quantitatively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
