Related papers: CoFiNet: Reliable Coarse-to-fine Correspondences f…

Camouflaged Object Detection (COD) is a critical aspect of computer vision aimed at identifying concealed objects, with applications spanning military, industrial, medical and monitoring domains. To address the problem of poor detail…

Facial landmark localization plays an important role in face recognition and analysis applications. In this paper, we give a brief introduction to a coarse-to-fine pipeline with neural networks and sequential regression. First, a global…

Recently, many approaches have been proposed through single or multiple representations to improve the performance of point cloud semantic segmentation. However, these works do not maintain a good balance among performance, efficiency, and…

Registering urban point clouds is a quite challenging task due to the large-scale, noise and data incompleteness of LiDAR scanning data. In this paper, we propose SARNet, a novel semantic augmented registration network aimed at achieving…

Matching cross-modality features between images and point clouds is a fundamental problem for image-to-point cloud registration. However, due to the modality difference between images and points, it is difficult to learn robust and…

We study the problem of coarse-grained response selection in retrieval-based dialogue systems. The problem is equally important with fine-grained response selection, but is less explored in existing literature. In this paper, we propose a…

Few prior works study deep learning on point sets. PointNet by Qi et al. is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting its ability to…

The task of point cloud upsampling aims to acquire dense and uniform point sets from sparse and irregular point sets. Although significant progress has been made with deep learning models, state-of-the-art methods require ground-truth dense…

Registration is a basic yet crucial task in point cloud processing. In correspondence-based point cloud registration, matching correspondences by point feature techniques may lead to an extremely high outlier ratio. Current methods still…

3D point cloud has been widely used in many mobile application scenarios, including autonomous driving and 3D sensing on mobile devices. However, existing 3D point cloud models tend to be large and cumbersome, making them hard to deploy on…

Point clouds produced by 3D scanning are often sparse, non-uniform, and noisy. Recent upsampling approaches aim to generate a dense point set, while achieving both distribution uniformity and proximity-to-surface, and possibly amending…

Point cloud registration has seen significant advancements with the application of deep learning techniques. However, existing approaches often overlook the potential of integrating radiometric information from RGB images. This limitation…

Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. Mainstream methods (e.g., PCN and TopNet) use Multi-layer Perceptrons (MLPs) to directly process point clouds, which…

Selection is a fundamental task in exploratory analysis and visualization of 3D point clouds. Prior researches on selection methods were developed mainly based on heuristics such as local point density, thus limiting their applicability in…

Robust point cloud registration is a fundamental task in 3D computer vision and geometric deep learning, essential for applications such as large-scale 3D reconstruction, augmented reality, and scene understanding. However, the performance…

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…

The rapid development of point cloud learning has driven point cloud completion into a new era. However, the information flows of most existing completion methods are solely feedforward, and high-level information is rarely reused to…

Outdoor LiDAR point clouds are typically large-scale and complexly distributed. To achieve efficient and accurate registration, emphasizing the similarity among local regions and prioritizing global local-to-local matching is of utmost…

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…

Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration. Despite the increasing popularity of introducing deep learning methods in this field, spatial consistency, which is…