3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions

By Dong Wook Shu, Sung Woo Park, Junseok Kwon. IEEE International Conference on Computer Vision, 2019

342 citations recorded by the source corpus.

In this paper, we propose a novel generative adversarial network (GAN) for 3D point clouds generation, which is called tree-GAN. To achieve state-of-the-art performance for multi-class 3D point cloud generation, a tree-structured graph convolution network (TreeGCN) is introduced as a generator for tree-GAN. Because TreeGCN performs graph convolutions within a tree, it can use ancestor information to boost the representation power for features. To evaluate GANs for 3D point clouds accurately, we develop a novel evaluation metric called Fr\'echet point cloud distance (FPD). Experimental results demonstrate that the proposed tree-GAN outperforms state-of-the-art GANs in terms of both conventional metrics and FPD, and can generate point clouds for different semantic parts without prior knowledge.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c7abade5be44b822475401008549271daa2f2009

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion (2020, methodology): “Recent architectures apply kernel point convolutions [67], tree-based graph convolutions [60], and normalizing flows [77].”
3D Shape Generation and Completion through Point-Voxel Diffusion (2021, background): “Many prior works have explored point cloud generation in terms of autoencoding [1, 11, 47], single-view reconstruction [12, 10, 18, 17], and adversarial generation [34, 48, 40].”
Diffusion Probabilistic Models for 3D Point Cloud Generation (2021, methodology): “We quantitatively compare our method with the following state-of-the-art generative models: PC-GAN [1], GCN-GAN [22], TreeGAN [19], PointFlow [25] and ShapeGF [2] using point clouds from two categories in ShapeNet: airplane and chair .”
Neural Unsigned Distance Fields for Implicit Function Learning (2020, methodology): “For point clouds (PCs) the pioneering PointNet based architectures [60, 61] spearheaded research, such as kernel point convolutions [73, 59, 33, 79], tree-based graph convolutions [68] normalizing ﬂows [85], combinations of points and voxels for eﬃciency [46] or domain adaptation techniques [62].”
A Survey on Generative Adversarial Networks: Variants, Applications, and Training (2020, methodology): “Ns have utilized in many other 3D image generation applications such as 3D-CGAN [83] uses paired training data for the generation of 3D-samples in different and controllable rotation angles, Tree-GAN [84] for 3D point cloud generation of multi-class applications, and 3D GAN (3DGAN) [85] that produce”
Unsupervised 3D Shape Completion through GAN Inversion (2021, methodology): “in the test set using Minimum Matching Distance-Earth Mover’s Distance (MMD-EMD) [1, 27].”
LION: Latent Point Diffusion Models for 3D Shape Generation (2022, methodology): “Other progressive [22, 37] and graph-based architectures [4, 6] have been used, too.”
Learning Gradient Fields for Shape Generation (2020, positive): “N×3 where N is predefined) [2,18,67,56,68,17,52,59], or relies on heuristic set distance functions such as Chamfer distance and Earth Mover Distance [25,65,19,12,6].”
MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers (2023, background): “Early works involved GANs for synthesizing point locations [30, 54, 59] and latent shape codes [1].”