相关论文: Point Cloud Generation using Transformer Encoders …

We propose a new framework that formulates point cloud registration as a denoising diffusion process from noisy transformation to object transformation. During training stage, object transformation diffuses from ground-truth transformation…

For the process of single top quark production within the "simplified model" with a scalar dark matter mediator, a new variable based on angular correlations was presented, for the proper reconstruction of which it is necessary to separate…

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…

Event-based motion field estimation is an important task. However, current optical flow methods face challenges: learning-based approaches, often frame-based and relying on CNNs, lack cross-domain transferability, while model-based methods,…

We describe a simple pre-training approach for point clouds. It works in three steps: 1. Mask all points occluded in a camera view; 2. Learn an encoder-decoder model to reconstruct the occluded points; 3. Use the encoder weights as…

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…

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,…

Classifying whole images is a classic problem in machine learning, and graph neural networks are a powerful methodology to learn highly irregular geometries. It is often the case that certain parts of a point cloud are more important than…

We present a neural network-enhanced column generation (CG) approach for a parallel machine scheduling problem. The proposed approach utilizes an encoder-decoder attention model, namely the transformer and pointer architectures, to develop…

Point Cloud Registration (PCR) is a critical and challenging task in computer vision. One of the primary difficulties in PCR is identifying salient and meaningful points that exhibit consistent semantic and geometric properties across…

Recently proposed normalizing flow models such as Glow have been shown to be able to generate high quality, high dimensional images with relatively fast sampling speed. Due to their inherently restrictive architecture, however, it is…

Generative models have proven effective at modeling 3D shapes and their statistical variations. In this paper we investigate their application to point clouds, a 3D shape representation widely used in computer vision for which, however,…

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,…

This work addresses the problem of point cloud registration using deep neural networks. We propose an approach to predict the alignment between two point clouds with overlapping data content, but displaced origins. Such point clouds…

We present a probabilistic model for point cloud generation, which is fundamental for various 3D vision tasks such as shape completion, upsampling, synthesis and data augmentation. Inspired by the diffusion process in non-equilibrium…

We apply a unified machine-learning framework based on Normalizing Flows (NFs) for the event-by-event reconstruction of invisible momenta and the subsequent evaluation of spin-sensitive observables in top-quark pair and dark-matter (DM)…

Central to our understanding of chemical reactivity is the principle of mass conservation, which is fundamental for ensuring physical consistency, balancing equations, and guiding reaction design. However, data-driven computational models…

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…

Modern image encoders achieve high generalization by decoupling semantic meaning from resolution, an ability yet to be fully realized in the 3D domain. We investigate the failure of 3D point cloud encoders to achieve similar generalization…

Normalizing flows are a class of probabilistic generative models which allow for both fast density computation and efficient sampling and are effective at modelling complex distributions like images. A drawback among current methods is…