SP-GAN not only enables the generation of diverse and realistic shapes as point clouds with fine details (see the two chairs on the left and right) but also embeds a dense correspondence across the generated shapes, thus facilitating part-wise interpolation between user-selected local parts in the generated shapes. Note how the left chair’s back (blue part in top arc) and the right chair’s legs (red part in bottom arc) morph in the two sequences.
We present SP-GAN, a new unsupervised sphere-guided generative model for direct synthesis of 3D shapes in the form of point clouds. Compared with existing models, SP-GAN is able to synthesize diverse and high-quality shapes with fine details and promote controllability for part-aware shape generation and manipulation, yet trainable without any parts annotations. In SP-GAN, we incorporate a global prior (uniform points on a sphere) to spatially guide the generative process and attach a local prior (a random latent code) to each sphere point to provide local details. The key insight in our design is to disentangle the complex 3D shape generation task into a global shape modeling and a local structure adjustment, to ease the learning process and enhance the shape generation quality. Also, our model forms an implicit dense correspondence between the sphere points and points in every generated shape, enabling various forms of structure-aware shape manipulations such as part editing, part-wise shape interpolation, and multi-shape part composition, etc., beyond the existing generative models. Experimental results, which include both visual and quantitative evaluations, demonstrate that our model is able to synthesize diverse point clouds with fine details and less noise, as compared with the state-of-the-art models.
@article{li2021spgan,
title={SP-GAN:Sphere-Guided 3D Shape Generation and Manipulation},
author={Li, Ruihui and Li, Xianzhi and Hui, Ke-Hei and Fu, Chi-Wing},
journal={ACM Transactions on Graphics (Proc. SIGGRAPH)},
volume={40},
number={4},
year={2021},
publisher={ACM}
}