DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion

• URL: http://arxiv.org/abs/2305.01921v3
• Date: Sun, 20 Aug 2023 22:57:46 GMT
• Title: DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion
• Authors: Kiyohiro Nakayama, Mikaela Angelina Uy, Jiahui Huang, Shi-Min Hu, Ke Li, Leonidas J Guibas
• Abstract summary: We introduce DiffFacto, a novel probabilistic generative model that learns the distribution of shapes with part-level control. Experiments show that our method is able to generate novel shapes with multiple axes of control. It achieves state-of-the-art part-level generation quality and generates plausible and coherent shapes.
• Score: 68.39543754708124
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While the community of 3D point cloud generation has witnessed a big growth in recent years, there still lacks an effective way to enable intuitive user control in the generation process, hence limiting the general utility of such methods. Since an intuitive way of decomposing a shape is through its parts, we propose to tackle the task of controllable part-based point cloud generation. We introduce DiffFacto, a novel probabilistic generative model that learns the distribution of shapes with part-level control. We propose a factorization that models independent part style and part configuration distributions and presents a novel cross-diffusion network that enables us to generate coherent and plausible shapes under our proposed factorization. Experiments show that our method is able to generate novel shapes with multiple axes of control. It achieves state-of-the-art part-level generation quality and generates plausible and coherent shapes while enabling various downstream editing applications such as shape interpolation, mixing, and transformation editing. Project website: https://difffacto.github.io/

Related papers

• Make-A-Shape: a Ten-Million-scale 3D Shape Model [52.701745578415796]
  This paper introduces Make-A-Shape, a new 3D generative model designed for efficient training on a vast scale. We first innovate a wavelet-tree representation to compactly encode shapes by formulating the subband coefficient filtering scheme. We derive the subband adaptive training strategy to train our model to effectively learn to generate coarse and detail wavelet coefficients.
  arXiv  Detail & Related papers  (2024-01-20T00:21:58Z)
• Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation [29.818827785812086]
  Controllable generation of 3D assets is important for many practical applications like content creation in movies, games and engineering, as well as in AR/VR. We present a suitable representation for 3D diffusion models to enable disentanglement by introducing a hybrid point cloud and neural radiance field approach.
  arXiv  Detail & Related papers  (2023-12-21T18:46:27Z)
• Patch-Wise Point Cloud Generation: A Divide-and-Conquer Approach [83.05340155068721]
  We devise a new 3d point cloud generation framework using a divide-and-conquer approach. All patch generators are based on learnable priors, which aim to capture the information of geometry primitives. Experimental results on a variety of object categories from the most popular point cloud dataset, ShapeNet, show the effectiveness of the proposed patch-wise point cloud generation.
  arXiv  Detail & Related papers  (2023-07-22T11:10:39Z)
• Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulation [54.09274684734721]
  We present a new approach for 3D shape generation, inversion, and manipulation, through a direct generative modeling on a continuous implicit representation in wavelet domain. Specifically, we propose a compact wavelet representation with a pair of coarse and detail coefficient volumes to implicitly represent 3D shapes via truncated signed distance functions and multi-scale biorthogonal wavelets. We may jointly train an encoder network to learn a latent space for inverting shapes, allowing us to enable a rich variety of whole-shape and region-aware shape manipulations.
  arXiv  Detail & Related papers  (2023-02-01T02:47:53Z)
• Autoregressive 3D Shape Generation via Canonical Mapping [92.91282602339398]
  transformers have shown remarkable performances in a variety of generative tasks such as image, audio, and text generation. In this paper, we aim to further exploit the power of transformers and employ them for the task of 3D point cloud generation. Our model can be easily extended to multi-modal shape completion as an application for conditional shape generation.
  arXiv  Detail & Related papers  (2022-04-05T03:12:29Z)
• EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation [19.817166425038753]
  This paper tackles the problem of parts-aware point cloud generation. A simple modification of the Variational Auto-Encoder yields a joint model of the point cloud itself. In addition to the flexibility afforded by our disentangled representation, the inductive bias introduced by our joint modelling approach yields the state-of-the-art experimental results on the ShapeNet dataset.
  arXiv  Detail & Related papers  (2021-10-13T12:38:01Z)
• Diffusion Probabilistic Models for 3D Point Cloud Generation [12.257593992442732]
  We present a probabilistic model for point cloud generation that is critical for various 3D vision tasks. Inspired by the diffusion process in non-equilibrium thermodynamics, we view points in point clouds as particles in a thermodynamic system in contact with a heat bath. We derive the variational bound in closed form for training and provide implementations of the model.
  arXiv  Detail & Related papers  (2021-03-02T03:56:02Z)
• LPMNet: Latent Part Modification and Generation for 3D Point Clouds [3.04585143845864]
  We propose a single end-to-end Autoencoder model that can handle generation and modification of both semantic parts, and global shapes. The proposed method supports part exchange between 3D point cloud models and composition by different parts to form new models by directly editing latent representations.
  arXiv  Detail & Related papers  (2020-08-08T17:24:37Z)
• MRGAN: Multi-Rooted 3D Shape Generation with Unsupervised Part Disentanglement [49.05682172235875]
  We present MRGAN, a multi-rooted adversarial network which generates part-disentangled 3D point-cloud shapes without part-based shape supervision. The network fuses multiple branches of tree-structured graph convolution layers which produce point clouds, with learnable constant inputs at the tree roots.
  arXiv  Detail & Related papers  (2020-07-25T14:41:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.