Proceedings Article10.1109/wacvw60836.2024.00057
Generating Point Cloud Augmentations via Class-Conditioned Diffusion Model
Gulshan Sharma,Chetan Gupta,Aastha Agarwal,Lalit Sharma,A. Dhall +4 more
- 01 Jan 2024
pp 480-488
4
TL;DR: The findings suggest that the proposed approach effectively generates high-quality synthetic embeddings directly from the Gaussian noise and improves the classification performance of the point cloud classes within limited data settings.
read more
Abstract: In this paper, we present a class-conditioned Denoising Diffusion Probabilistic Model (DDPM) based approach to augment point cloud data within the latent feature space. Our method focuses on generating synthetic point cloud la-tent embeddings, which encode both spatial and semantic information of the point cloud. By harnessing the capabil-ities of DDPM within a class-conditioned framework, our goal is to provide a cost-effective and practical solution for the augmentation of point cloud samples. We conduct ex-periments on the publicly available point cloud dataset, and our findings suggest that the proposed approach (a) effectively generates high-quality synthetic embeddings directly from the Gaussian noise and (b) improves the classification performance of the point cloud classes within limited data settings.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Advancing 3D point cloud understanding through deep transfer learning: A comprehensive survey
Shahab Saquib Sohail,Yassine Himeur,Hamza Kheddar,Abbes Amira,Fodil Fadli,Shadi Atalla,Abigail Copiaco,W. Mansoor +7 more
TL;DR: A comprehensive overview of the latest techniques for understanding 3DPC using DTL and domain adaptation using various applications, such as 3DPC object detection, semantic labeling, segmentation, classification, registration, downsampling/upsampling, and denoising is provided.
10
Imbalanced spectral data analysis using data augmentation based on the generative adversarial network
Jihoon Chung,Junru Zhang,Amirul Islam Saimon,Yang Liu,Blake N. Johnson,Zhenyu Kong +5 more
TL;DR: Imbalanced spectral data analysis using data augmentation based on generative adversarial network (GAN) improves classification performance by generating balanced training data.
ClipSwap: Towards High Fidelity Face Swapping via Attributes and CLIP-Informed Loss
Penny L. Yee,Sudeepta Mishra,Abhinav Dhall +2 more
- 27 May 2024
TL;DR: The proposed ClipSwap outperforms prior state-of-the-art (SOTA) methods in face swapping, particularly in terms of identity transfer and facial attribute features.
Synthetic Data Generation for Accurate, Fair, and Private Recommender Systems
Derek Lilienthal
- 21 Aug 2024
References
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
- 08 Dec 2014
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
•Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
R. Qi Charles,Hao Su,Mo Kaichun,Leonidas J. Guibas +3 more
- 21 Jul 2017
TL;DR: This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
•Posted Content
Denoising Diffusion Probabilistic Models
TL;DR: High quality image synthesis results are presented using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics, which naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding.