Autoregressive 3D Shape Completion via Sphere-Guided Disentangled Representation

This paper introduces a novel 3D shape completion method based on sphere-guided disentangled representation. Utilizing an autoregressive transformer-based model, our approach efficiently constructs object completion distributions given incomplete point clouds. To enhance completion modeling, we propose sDVQ-DIF (sphere-guided disentangled vector quantized deep implicit function), a new approach using decoupled discrete variables to represent 3D shapes efficiently. Experimental results demonstrate our model's superior performance in terms of completion quality and fidelity compared to state-of-the-art methods, applicable to various shape types and incomplete patterns.