Related papers: Efficient Point Cloud Processing with High-Dimensi…

Convolutional Neural Networks (CNNs) have performed extremely well on data represented by regularly arranged grids such as images. However, directly leveraging the classic convolution kernels or parameter sharing mechanisms on sparse 3D…

We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds. Inspired by Bilateral Convolutional Layers (BCL), we propose novel DownBCL, UpBCL, and CorrBCL…

High-end ARM processors are emerging in data centers and HPC systems, posing as a strong contender to x86 machines. Memory-centric profiling is an important approach for dissecting an application's bottlenecks on memory access and guiding…

Human pose estimation focuses on predicting body keypoints to analyze human motion. Currently, most pose estimation tasks rely on conventional RGB cameras. In contrast, event cameras provide high temporal resolution and low latency,…

Point cloud upsampling is vital for the quality of the mesh in three-dimensional reconstruction. Recent research on point cloud upsampling has achieved great success due to the development of deep learning. However, the existing methods…

Producing traversability maps and understanding the surroundings are crucial prerequisites for autonomous navigation. In this paper, we address the problem of traversability assessment using point clouds. We propose a novel pillar feature…

We propose an end-to-end attribute compression method for dense point clouds. The proposed method combines a frequency sampling module, an adaptive scale feature extraction module with geometry assistance, and a global hyperprior entropy…

Learning per-point semantic features from the hierarchical feature pyramid is essential for point cloud semantic segmentation. However, most previous methods suffered from ambiguous region features or failed to refine per-point features…

Recently, state space models have exhibited strong global modeling capabilities and linear computational complexity in contrast to transformers. This research focuses on applying such architecture to more efficiently and effectively model…

As cloud services become increasingly integral to modern IT infrastructure, ensuring hardware reliability is essential to sustain high-quality service. Memory failures pose a significant threat to overall system stability, making accurate…

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…

Feature engineering continues to play a critical role in image classification, particularly when interpretability and computational efficiency are prioritized over deep learning models with millions of parameters. In this study, we revisit…

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention, but ignore their content and fail to establish relationships…

We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e.g., classification and segmentation. Unlike prior works, which were trained to optimize the weights of a pre-selected set of…

Both local details and global context are crucial in medical image segmentation, and effectively integrating them is essential for achieving high accuracy. However, existing mainstream methods based on CNN-Transformer hybrid architectures…

As we push the boundaries of performance in various vision tasks, the models grow in size correspondingly. To keep up with this growth, we need very aggressive pruning techniques for efficient inference and deployment on edge devices.…

This paper presents MinkUNeXt, an effective and efficient architecture for place-recognition from point clouds entirely based on the new 3D MinkNeXt Block, a residual block composed of 3D sparse convolutions that follows the philosophy…

Point cloud analysis has evolved with diverse network architectures, while existing works predominantly focus on introducing novel structural designs. However, conventional point-based architectures - processing raw points through…

The trade-off between feature representation power and spatial localization accuracy is crucial for the dense classification/semantic segmentation of aerial images. High-level features extracted from the late layers of a neural network are…

The convolutional-based methods provide good segmentation performance in the medical image segmentation task. However, those methods have the following challenges when dealing with the edges of the medical images: (1) Previous…