Related papers: A Lennard-Jones Layer for Distribution Normalizati…

Layer normalization (LN) is a ubiquitous technique in deep learning but our theoretical understanding to it remains elusive. This paper investigates a new theoretical direction for LN, regarding to its nonlinearity and representation…

We introduce Point-LN, a novel lightweight framework engineered for efficient 3D point cloud classification. Point-LN integrates essential non-parametric components-such as Farthest Point Sampling (FPS), k-Nearest Neighbors (k-NN), and…

Diffusion models have garnered considerable interest in computer vision, owing both to their capacity to synthesize photorealistic images and to their proven effectiveness in image reconstruction tasks. However, existing approaches fail to…

We address a data augmentation problem for LiDAR. Given a LiDAR scan of a scene from some position, how can one simulate new scans of that scene from different, secondary positions? The method defines criteria for selecting valid secondary…

Layer normalization (LayerNorm) is a technique to normalize the distributions of intermediate layers. It enables smoother gradients, faster training, and better generalization accuracy. However, it is still unclear where the effectiveness…

What lattice Lennard-Jones (LJ) solid favors, the lattice identification of simulated system and the microstructures of liquid and non-crystalline solid are three important questions in condensed physics and material science and are…

Much effort has been put into developing samplers with specific properties, such as producing blue noise, low-discrepancy, lattice or Poisson disk samples. These samplers can be slow if they rely on optimization processes, may rely on a…

Computer vision techniques play a central role in the perception stack of autonomous vehicles. Such methods are employed to perceive the vehicle surroundings given sensor data. 3D LiDAR sensors are commonly used to collect sparse 3D point…

The benefit of transformers in large-scale 3D point cloud perception tasks, such as 3D object detection, is limited by their quadratic computation cost when modeling long-range relationships. In contrast, linear RNNs have low computational…

In this article we describe a new convolutional neural network (CNN) to classify 3D point clouds of urban or indoor scenes. Solutions are given to the problems encountered working on scene point clouds, and a network is described that…

Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates cutting-edge learning-based techniques for shape analysis…

Recently, a number of iterative learning methods have been introduced to improve generalization. These typically rely on training for longer periods of time in exchange for improved generalization. LLF (later-layer-forgetting) is a…

Traditional convolution layers are specifically designed to exploit the natural data representation of images -- a fixed and regular grid. However, unstructured data like 3D point clouds containing irregular neighborhoods constantly breaks…

Point cloud analysis is challenging due to the irregularity of the point cloud data structure. Existing works typically employ the ad-hoc sampling-grouping operation of PointNet++, followed by sophisticated local and/or global feature…

Existing normal estimation methods for point clouds are often less robust to severe noise and complex geometric structures. Also, they usually ignore the contributions of different neighbouring points during normal estimation, which leads…

We present an adaptive sampling approach to 3D reconstruction of the welding joint using the point cloud that is generated by a laser sensor. We start with a randomized strategy to approximate the surface of the volume of interest through…

A novel multi-scale operator for unorganized 3D point clouds is introduced. The Difference of Normals (DoN) provides a computationally efficient, multi-scale approach to processing large unorganized 3D point clouds. The application of DoN…

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…

3D point cloud completion, the task of inferring the complete geometric shape from a partial point cloud, has been attracting attention in the community. For acquiring high-fidelity dense point clouds and avoiding uneven distribution,…

As 3D point clouds become a cornerstone of modern technology, the need for sophisticated generative models and reliable evaluation metrics has grown exponentially. In this work, we first expose that some commonly used metrics for evaluating…