Related papers: EPContrast: Effective Point-level Contrastive Lear…

To help bridge the gap between internet vision-style problems and the goal of vision for embodied perception we instantiate a large-scale navigation task -- Embodied Question Answering [1] in photo-realistic environments (Matterport 3D). We…

3D contrastive representation learning has exhibited remarkable efficacy across various downstream tasks. However, existing contrastive learning paradigms based on cosine similarity fail to deeply explore the potential intra-modal…

The reconstruction of real-world surfaces is on high demand in various applications. Most existing reconstruction approaches apply 3D scanners for creating point clouds which are generally sparse and of low density. These points clouds will…

Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences indistinguishably among 3D points, arising an intrinsic…

Recently, the fundamental problem of unsupervised domain adaptation (UDA) on 3D point clouds has been motivated by a wide variety of applications in robotics, virtual reality, and scene understanding, to name a few. The point cloud data…

Point cloud based retrieval for place recognition is still a challenging problem due to drastic appearance and illumination changes of scenes in changing environments. Existing deep learning based global descriptors for the retrieval task…

Recently, some contrastive learning methods have been proposed to simultaneously learn representations and clustering assignments, achieving significant improvements. However, these methods do not take the category information and…

As the basic task of point cloud analysis, classification is fundamental but always challenging. To address some unsolved problems of existing methods, we propose a network that captures geometric features of point clouds for better…

Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors. Existing top-down approaches tackle this problem by either…

Contrastive learning has moved the state of the art for many tasks in computer vision and information retrieval in recent years. This poster is the first work that applies supervised contrastive learning to the task of product matching in…

Contrastive learning is a method of learning visual representations by training Deep Neural Networks (DNNs) to increase the similarity between representations of positive pairs (transformations of the same image) and reduce the similarity…

Despite the recent development of deep learning-based point cloud upsampling, most MLP-based point cloud upsampling methods have limitations in that it is difficult to train the local and global structure of the point cloud at the same…

Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…

Deep learning is increasingly being used to perform machine vision tasks such as classification, object detection, and segmentation on 3D point cloud data. However, deep learning inference is computationally expensive. The limited…

Transfer learning has long been a key factor in the advancement of many fields including 2D image analysis. Unfortunately, its applicability in 3D data processing has been relatively limited. While several approaches for point cloud…

Graph contrastive learning (GCL) has emerged as a pivotal technique in the domain of graph representation learning. A crucial aspect of effective GCL is the caliber of generated positive and negative samples, which is intrinsically dictated…

We propose Point-PNG, a novel self-supervised learning framework that generates conditional pseudo-negatives in the latent space to learn point cloud representations that are both discriminative and transformation-sensitive. Conventional…

Neural networks have changed the way machines interpret the world. At their core, they learn by following gradients, adjusting their parameters step by step until they identify the most discriminant patterns in the data. This process gives…

Vision transformers (ViTs) have recently been widely applied to 3D point cloud understanding, with masked autoencoding as the predominant pre-training paradigm. However, the challenge of learning dense and informative semantic features from…

This paper presents Contrastive Transformer, a contrastive learning scheme using the Transformer innate patches. Contrastive Transformer enables existing contrastive learning techniques, often used for image classification, to benefit dense…