Related papers: HD2Reg: Hierarchical Descriptors and Detectors for…

3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation.…

We present SKD, a novel keypoint detector that uses saliency to determine the best candidates from a point cloud for tasks such as registration and reconstruction. The approach can be applied to any differentiable deep learning descriptor…

The introduction of inexpensive 3D data acquisition devices has promisingly facilitated the wide availability and popularity of 3D point cloud, which attracts more attention to the effective extraction of novel 3D point cloud descriptors…

We present an approach to learning features that represent the local geometry around a point in an unstructured point cloud. Such features play a central role in geometric registration, which supports diverse applications in robotics and 3D…

We present a novel differential matching algorithm for 3D point cloud registration. Instead of only optimizing the feature extractor for a matching algorithm, we propose a learning-based matching module optimized to the jointly-trained…

We propose a novel framework to learn 3D point cloud semantics from 2D multi-view image observations containing pose error. On the one hand, directly learning from the massive, unstructured and unordered 3D point cloud is computationally…

The Discriminative Optimization (DO) algorithm has been proved much successful in 3D point cloud registration. In the original DO, the feature (descriptor) of two point cloud was defined as a histogram, and the element of histogram…

We propose an efficient method to learn deep local descriptors for instance-level recognition. The training only requires examples of positive and negative image pairs and is performed as metric learning of sum-pooled global image…

In this paper, we propose a deep hierarchical attention context model for lossless attribute compression of point clouds, leveraging a multi-resolution spatial structure and residual learning. A simple and effective Level of Detail (LoD)…

Robust and discriminative feature learning is critical for high-quality point cloud registration. However, existing deep learning-based methods typically rely on Euclidean neighborhood-based strategies for feature extraction, which struggle…

Point cloud processing is a challenging task due to its sparsity and irregularity. Prior works introduce delicate designs on either local feature aggregator or global geometric architecture, but few combine both advantages. We propose…

Point clouds are collected nowadays from a plethora of sensors, some having higher accuracies and higher costs, some having lower accuracies but also lower costs. Not only there is a large choice for different sensors, but also these can be…

The use of local detectors and descriptors in typical computer vision pipelines work well until variations in viewpoint and appearance change become extreme. Past research in this area has typically focused on one of two approaches to this…

Exploring contextual information in the local region is important for shape understanding and analysis. Existing studies often employ hand-crafted or explicit ways to encode contextual information of local regions. However, it is hard to…

We propose an attentive local feature descriptor suitable for large-scale image retrieval, referred to as DELF (DEep Local Feature). The new feature is based on convolutional neural networks, which are trained only with image-level…

Several SLAM methods benefit from the use of semantic information. Most integrate photometric methods with high-level semantics such as object detection and semantic segmentation. We propose that adding a semantic segmentation decoder in a…

Feature matching is a fundamental problem in computer vision with wide-ranging applications, including simultaneous localization and mapping (SLAM), image stitching, and 3D reconstruction. While recent advances in deep learning have…

Given the prominence of current 3D sensors, a fine-grained analysis on the basic point cloud data is worthy of further investigation. Particularly, real point cloud scenes can intuitively capture complex surroundings in the real world, but…

Point cloud-based object/place recognition remains a problem of interest in applications such as autonomous driving, scene reconstruction, and localization. Extracting a meaningful global descriptor from a query point cloud that can be…

Common deep learning models for 3D environment perception often use pillarization/voxelization methods to convert point cloud data into pillars/voxels and then process it with a 2D/3D convolutional neural network (CNN). The pioneer work…