相关论文: Point-DAE: Denoising Autoencoders for Self-supervi…

Autonomous driving is the key technology of intelligent logistics in Industrial Internet of Things (IIoT). In autonomous driving, the appearance of incomplete point clouds losing geometric and semantic information is inevitable owing to…

We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during…

The purpose of intrinsic decomposition is to separate an image into its albedo (reflective properties) and shading components (illumination properties). This is challenging because it's an ill-posed problem. Conventional approaches…

Point cloud data now are popular data representations in a number of three-dimensional (3D) vision research realms. However, due to the limited performance of sensors and sensing noise, the raw data usually suffer from sparsity, noise, and…

Recent work has shown how denoising and contractive autoencoders implicitly capture the structure of the data-generating density, in the case where the corruption noise is Gaussian, the reconstruction error is the squared error, and the…

Advances in self-supervised learning are essential for enhancing feature extraction and understanding in point cloud processing. This paper introduces PMT-MAE (Point MLP-Transformer Masked Autoencoder), a novel self-supervised learning…

We present SeRP, a framework for Self-Supervised Learning of 3D point clouds. SeRP consists of encoder-decoder architecture that takes perturbed or corrupted point clouds as inputs and aims to reconstruct the original point cloud without…

The ever-increasing 3D application makes the point cloud compression unprecedentedly important and needed. In this paper, we propose a patch-based compression process using deep learning, focusing on the lossy point cloud geometry…

Self-supervised methods have been proven effective for learning deep representations of 3D point cloud data. Although recent methods in this domain often rely on random masking of inputs, the results of this approach can be improved. We…

Local density of point clouds is crucial for representing local details, but has been overlooked by existing point cloud compression methods. To address this, we propose a novel deep point cloud compression method that preserves local…

Established sampling protocols for 3D point cloud learning, such as Farthest Point Sampling (FPS) and Fixed Sample Size (FSS), have long been relied upon. However, real-world data often suffer from corruptions, such as sensor noise, which…

Embracing the deep learning techniques for representation learning in clustering research has attracted broad attention in recent years, yielding a newly developed clustering paradigm, viz. the deep clustering (DC). Typically, the DC models…

In this study, we examine the representation learning abilities of Denoising Diffusion Models (DDM) that were originally purposed for image generation. Our philosophy is to deconstruct a DDM, gradually transforming it into a classical…

Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$\beta$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with…

Auto-encoder is an important architecture to understand point clouds in an encoding and decoding procedure of self reconstruction. Current auto-encoder mainly focuses on the learning of global structure by global shape reconstruction, while…

While deep neural networks have been shown to perform remarkably well in many machine learning tasks, labeling a large amount of ground truth data for supervised training is usually very costly to scale. Therefore, learning robust…

Masked point modeling methods have recently achieved great success in self-supervised learning for point cloud data. However, these methods are sensitive to rotations and often exhibit sharp performance drops when encountering rotational…

Great progress has been made in point cloud classification with learning-based methods. However, complex scene and sensor inaccuracy in real-world application make point cloud data suffer from corruptions, such as occlusion, noise and…

Point cloud denoising task aims to recover the clean point cloud from the scanned data coupled with different levels or patterns of noise. The recent state-of-the-art methods often train deep neural networks to update the point locations…

The precision of shape representation and the dimensionality of the design space significantly influence the cost and outcomes of aerodynamic optimization. The design space can be represented more compactly by maintaining geometric…