Related papers: Point-DAE: Denoising Autoencoders for Self-supervi…

Self-supervised auto-encoders have emerged as a successful framework for representation learning in computer vision and natural language processing in recent years, However, their application to graph data has been met with limited…

Compared to 2D data, the scale of point cloud data in different domains available for training, is quite limited. Researchers have been trying to combine these data of different domains for masked autoencoder (MAE) pre-training to leverage…

Anomaly detection is the task of recognising novel samples which deviate significantly from pre-establishednormality. Abnormal classes are not present during training meaning that models must learn effective rep-resentations solely across…

LiDAR-based perception is central to autonomous driving and robotics, yet raw point clouds remain highly vulnerable to noise, occlusion, and adversarial corruptions. Autoencoders offer a natural framework for denoising and reconstruction,…

Real-world environment-derived point clouds invariably exhibit noise across varying modalities and intensities. Hence, point cloud denoising (PCD) is essential as a preprocessing step to improve downstream task performance. Deep learning…

Effective image restoration with large-size corruptions, such as blind image inpainting, entails precise detection of corruption region masks which remains extremely challenging due to diverse shapes and patterns of corruptions. In this…

The Denoising Autoencoder (DAE) enhances the flexibility of the data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves an in-depth study because it characterizes a fixed…

Masked auto-encoding is a popular and effective self-supervised learning approach to point cloud learning. However, most of the existing methods reconstruct only the masked points and overlook the local geometry information, which is also…

Point clouds obtained from capture devices or 3D reconstruction techniques are often noisy and interfere with downstream tasks. The paper aims to recover the underlying surface of noisy point clouds. We design a novel model, NoiseTrans,…

We show that denoising of 3D point clouds can be learned unsupervised, directly from noisy 3D point cloud data only. This is achieved by extending recent ideas from learning of unsupervised image denoisers to unstructured 3D point clouds.…

Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training. This paper shows that…

Self-supervised learning is attracting large attention in point cloud understanding. However, exploring discriminative and transferable features still remains challenging due to their nature of irregularity and sparsity. We propose a…

Point clouds obtained with 3D scanners or by image-based reconstruction techniques are often corrupted with significant amount of noise and outliers. Traditional methods for point cloud denoising largely rely on local surface fitting (e.g.,…

Interpretability is essential for user trust in real-world anomaly detection applications. However, deep learning models, despite their strong performance, often lack transparency. In this work, we study the interpretability of…

Denoising diffusion probabilistic models (DDPMs) have shown impressive results on sequence generation by iteratively corrupting each example and then learning to map corrupted versions back to the original. However, previous work has…

Masked Autoencoders learn strong visual representations and achieve state-of-the-art results in several independent modalities, yet very few works have addressed their capabilities in multi-modality settings. In this work, we focus on point…

Achieving robust 3D perception in the face of corrupted data presents an challenging hurdle within 3D vision research. Contemporary transformer-based point cloud recognition models, albeit advanced, tend to overfit to specific patterns,…

We propose a Point-Voxel DeConvolution (PVDeConv) module for 3D data autoencoder. To demonstrate its efficiency we learn to synthesize high-resolution point clouds of 10k points that densely describe the underlying geometry of Computer…

Point cloud denoising aims to restore clean point clouds from raw observations corrupted by noise and outliers while preserving the fine-grained details. We present a novel deep learning-based denoising model, that incorporates normalizing…

Masked Autoencoder (MAE) is a self-supervised approach for representation learning, widely applicable to a variety of downstream tasks in computer vision. In spite of its success, it is still not fully uncovered what and how MAE exactly…