Learning Representations and Generative Models for 3D Point Clouds

By Panos Achlioptas, Olga Diamanti, Ioannis Mitliagkas, Leonidas J. Guibas. 2017

1,682 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Object-Centric Learning with Slot Attention (2020, methodology): “Set representations are commonly used in tasks across many data modalities ranging from point cloud prediction [29, 30], classifying multiple objects in an image [31], or generation of molecules with desired properties [32, 33].”
Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation (2021, background): “…this paper, most existing set predictors are either not multiset-equivariant (Vinyals et al., 2016; Stewart & Andriluka, 2016; Vaswani et al., 2017; Achlioptas et al., 2018; Li et al., 2018; Rezatoﬁghi et al., 2020) or set-equivariant (Lee et al., 2019; Locatello et al., 2020; Kosiorek et al.,…”
Occupancy Networks: Learning 3D Reconstruction in Function Space (2018, background): “Point clouds [1,17] and meshes [34,57,70] have been introduced as alternative representations for deep learning, using appropriate loss functions.”
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation (2019, methodology): “PointNet [38, 39], for example, uses max-pool operations to extract global shape features, and the technique is widely used as an encoder for point generation networks [57, 1].”
Learning Implicit Fields for Generative Shape Modeling (2018, methodology): “We also compared our results with two state-of-the-art methods, 3DGAN [45] and the generative model for point clouds in [1] (PC-GAN).”
Diffusion Probabilistic Models for 3D Point Cloud Generation (2021, methodology): “[1] employ generative adversarial networks [8] based on a pre-trained auto-encoder.”
Sphere Generative Adversarial Network Based on Geometric Moment Matching (2019, methodology): “[8], generative adversarial networks (GANs) have attracted much research interest, and they have been used to achieve outstanding performance in a wide range of computer vision applications including in image generation [17, 26], super resolution [14], video prediction [19], style transfer [5, 12, 3”
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts (2020, methodology): “Following suit, recent works attempt to adapt the 2D pretext tasks to 3D, but mostly focus on single object classiﬁcation tasks on ShapeNet [1, 17, 70, 22, 37, 62, 26, 51, 50].”
SO-Net: Self-Organizing Network for Point Cloud Analysis (2018, background): “The most related work is the point set generation network [13] and the point cloud generative models [1].”
Visual Object Networks: Image Generation with Disentangled 3D Representations (2018, background): “Popular representations include voxels [Wu et al., 2016], point clouds [Gadelha et al., 2017b, Achlioptas et al., 2018], and octave trees [Tatarchenko et al., 2017].”
Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds (2020, methodology): “Self-Reconstruction: Self-reconstruction, or point autoencoding, is a widely used technique for unsupervised point cloud representation learning [1,8,14,26,47,55,56].”
HyperCube: Implicit Field Representations of Voxelized 3D Models (2021, background): “3D objects can be represented using different approaches including voxel grids [4, 5, 6, 7], octrees [8, 9, 10, 11], multi-view images [12, 13, 14], point clouds [15, 16, 17, 18, 19], geometry images [20, 21], deformable meshes [5, 21, 22, 19], and part-based structural graphs [23, 24].”
MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers (2023, methodology): “For BSP-Net and AtlasNet, which are built on autoencoder back-bones, we follow [1] to fit a Gaussian mixture model with 32 components to enable unconditional sampling of shapes.”
Unsupervised 3D Shape Completion through GAN Inversion (2021, methodology): “Minimum Matching Distance (MMD) [1] measures the fidelity of a set of generated shapes Sc with respect to the set of ground truth shapes Sgt. Specifically, we match every shape xgt in Sgt to the generated shape xc in Sc with minimum distance, and report the average macthed distance.”
Shap-E: Generating Conditional 3D Implicit Functions (2023, methodology): “Achlioptas et al. [1] train an auto-encoder on point clouds, and experiment with both GANs [19] and GMMs [8] to model the resulting latent space.”
One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion (2023, background): “…3D native generative models that learn directly from 3D synthetic data or real scans and generate various 3D representations such as point clouds [1, 15, 41, 47, 83], 3D voxels [9, 59, 74, 75], polygon meshes [16, 17, 26, 32, 37, 46, 68], parametric models [21], and implicit fields [8, 14, 19,…”