SC-Diff: 3D Shape Completion with Latent Diffusion Models

arXiv:2403.12470v1 Announce Type: new
Abstract: This paper introduces a 3D shape completion approach using a 3D latent diffusion model optimized for completing shapes, represented as Truncated Signed Distance Functions (TSDFs), from partial 3D scans. Our method combines image-based conditioning through cross-attention and spatial conditioning through the integration of 3D features from captured partial scans. This dual guidance enables high-fidelity, realistic shape completions at superior resolutions. At the core of our approach is the compression of 3D data into a low-dimensional …

abstract arxiv attention cs.cv diff diffusion diffusion model diffusion models features functions image integration latent diffusion models paper scans spatial through type