Related papers: Point Cloud Transformers applied to Collider Physi…
Over the past five years, modern machine learning has been quietly revolutionizing particle physics. Old methodology is being outdated and entirely new ways of thinking about data are becoming commonplace. This article will review some…
Semantic segmentation of point clouds, aiming to assign each point a semantic category, is critical to 3D scene understanding.Despite of significant advances in recent years, most of existing methods still suffer from either the…
While Transformers have achieved impressive success in natural language processing and computer vision, their performance on 3D point clouds is relatively poor. This is mainly due to the limitation of Transformers: a demanding need for…
Point clouds are unstructured and unordered data, as opposed to images. Thus, most machine learning approach developed for image cannot be directly transferred to point clouds. In this paper, we propose a generalization of discrete…
Place recognition is a fundamental component of robotics, and has seen tremendous improvements through the use of deep learning models in recent years. Networks can experience significant drops in performance when deployed in unseen or…
We propose a novel method that renders point clouds as if they are surfaces. The proposed method is differentiable and requires no scene-specific optimization. This unique capability enables, out-of-the-box, surface normal estimation,…
Learning 3D point sets with rotational invariance is an important and challenging problem in machine learning. Through rotational invariant architectures, 3D point cloud neural networks are relieved from requiring a canonical global pose…
We propose a novel approach aimed at object and semantic scene completion from a partial scan represented as a 3D point cloud. Our architecture relies on three novel layers that are used successively within an encoder-decoder structure and…
Point clouds and high-resolution 3D data have become increasingly important in various fields, including surveying, construction, and virtual reality. However, simply having this data is not enough; to extract useful information, semantic…
Pre-trained large-scale models have exhibited remarkable efficacy in computer vision, particularly for 2D image analysis. However, when it comes to 3D point clouds, the constrained accessibility of data, in contrast to the vast repositories…
We propose the use of a Transformer to accurately predict normals from point clouds with noise and density variations. Previous learning-based methods utilize PointNet variants to explicitly extract multi-scale features at different input…
Automatic synthesis of high quality 3D shapes is an ongoing and challenging area of research. While several data-driven methods have been proposed that make use of neural networks to generate 3D shapes, none of them reach the level of…
Reconstructing charged particle tracks is a fundamental task in modern collider experiments. The unprecedented particle multiplicities expected at the High-Luminosity Large Hadron Collider (HL-LHC) pose significant challenges for track…
Recently the Transformer structure has shown good performances in graph learning tasks. However, these Transformer models directly work on graph nodes and may have difficulties learning high-level information. Inspired by the vision…
Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel…
This paper aims at bringing some light and understanding to the field of deep learning for dynamic point cloud processing. Specifically, we focus on the hierarchical features learning aspect, with the ultimate goal of understanding which…
Recently, the pre-training paradigm combining Transformer and masked language modeling has achieved tremendous success in NLP, images, and point clouds, such as BERT. However, directly extending BERT from NLP to point clouds requires…
This article proposes a novel unsupervised learning framework for detecting the number of tunnel junctions in subterranean environments based on acquired 2D point clouds. The implementation of the framework provides valuable information for…
Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector, followed by different temporal aggregation…
Jet interactions in a hot QCD medium created in heavy-ion collisions are conventionally assessed by measuring the modification of the distributions of jet observables with respect to the proton-proton baseline. However, the steeply falling…