Repurposing 2D Diffusion Models for 3D Shape Completion
This addresses the challenge of 3D shape completion for applications like computer graphics and robotics, offering a practical solution by repurposing existing 2D models, though it is incremental in leveraging known techniques.
The paper tackles the problem of 3D shape completion from incomplete point clouds by adapting 2D diffusion models, achieving high-quality, detail-preserving completions validated on PCN and ShapeNet-55 datasets.
We present a framework that adapts 2D diffusion models for 3D shape completion from incomplete point clouds. While text-to-image diffusion models have achieved remarkable success with abundant 2D data, 3D diffusion models lag due to the scarcity of high-quality 3D datasets and a persistent modality gap between 3D inputs and 2D latent spaces. To overcome these limitations, we introduce the Shape Atlas, a compact 2D representation of 3D geometry that (1) enables full utilization of the generative power of pretrained 2D diffusion models, and (2) aligns the modalities between the conditional input and output spaces, allowing more effective conditioning. This unified 2D formulation facilitates learning from limited 3D data and produces high-quality, detail-preserving shape completions. We validate the effectiveness of our results on the PCN and ShapeNet-55 datasets. Additionally, we show the downstream application of creating artist-created meshes from our completed point clouds, further demonstrating the practicality of our method.