Autoregressive 3D Shape Completion via Sphere-Guided Disentangled Representation

Jiahui Li, Pourya Shamsolmoali, Yue LuICASSP 2024 · OpenReview

Abstract

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.
BibTeX
@inproceedings{li2024autoregressive,
  author = {Jiahui Li and Pourya Shamsolmoali and Yue Lu},
  title = {{Autoregressive 3D Shape Completion via Sphere-Guided Disentangled Representation}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2024},
  url = {https://openreview.net/forum?id=guiGYtmLq8},
}

Loading related content...

Figure