Make-A-Shape: a Ten-Million-scale 3D Shape Model

Ka-Hei HUI, Aditya SANGHI, Arianna RAMPINI, Kamal Rahimi MALEKSHAN, Zhengzhe LIU, Hooman SHAYANI, Chi-Wing FU*

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

1 Citation (Scopus)

Abstract

The progression in large-scale 3D generative models has been impeded by significant resource requirements for training and challenges like inefficient representations. This paper introduces Make-A-Shape, a novel 3D generative model trained on a vast scale, using 10 million publicly-available shapes. We first innovate the wavelet-tree representation to encode high-resolution SDF shapes with minimal loss, leveraging our newly-proposed subband coefficient filtering scheme. We then design a subband coefficient packing scheme to facilitate diffusion-based generation and a subband adaptive training strategy for effective training on the large-scale dataset. Our generative framework is versatile, capable of conditioning on various input modalities such as images, point clouds, and voxels, enabling a variety of downstream applications, e.g., unconditional generation, completion, and conditional generation. Our approach clearly surpasses the existing baselines in delivering high-quality results and can efficiently generate shapes within two seconds for most conditions.
Original languageEnglish
Title of host publicationProceedings of the 41st International Conference on Machine Learning, ICML 2024
EditorsRuslan SALAKHUTDINOV, Zico KOLTER, Katherine HELLER, Adrian WELLER, Nuria OLIVER, Jonathan SCARLETT, Felix BERKENKAMP
PublisherML Research Press
Pages20660-20681
Number of pages22
Publication statusPublished - 2024
Externally publishedYes

Publication series

NameProceedings of Machine Learning Research
PublisherML Research Press
Volume235
ISSN (Print)2640-3498

Bibliographical note

Publisher Copyright:
Copyright 2024 by the author(s)

Funding

This work is supported by the Research Grants Council of the Hong Kong Special Administrative Region, China [Project No.: CUHK 14201921].

Fingerprint

Dive into the research topics of 'Make-A-Shape: a Ten-Million-scale 3D Shape Model'. Together they form a unique fingerprint.

Cite this