Related papers: DetarNet: Decoupling Translation and Rotation by S…

Single image defocus deblurring (SIDD) aims to restore an all-in-focus image from a defocused one. Distribution shifts in defocused images generally lead to performance degradation of existing methods during out-of-distribution inferences.…

Modern Convolutional Neural Networks (CNN) are extremely powerful on a range of computer vision tasks. However, their performance may degrade when the data is characterised by large intra-class variability caused by spatial transformations.…

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…

We present 3DRegNet, a novel deep learning architecture for the registration of 3D scans. Given a set of 3D point correspondences, we build a deep neural network to address the following two challenges: (i) classification of the point…

Point scene understanding is a challenging task to process real-world scene point cloud, which aims at segmenting each object, estimating its pose, and reconstructing its mesh simultaneously. Recent state-of-the-art method first segments…

For autonomous driving, radar sensors provide superior reliability regardless of weather conditions as well as a significantly high detection range. State-of-the-art algorithms for environment perception based on radar scans build up on…

3D point clouds are often perturbed by noise due to the inherent limitation of acquisition equipments, which obstructs downstream tasks such as surface reconstruction, rendering and so on. Previous works mostly infer the displacement of…

Facial recognition using deep learning has been widely used in social life for applications such as authentication, smart door locks, and photo grouping, etc. More and more networks have been developed to facilitate computer vision tasks,…

Real-world environment-derived point clouds invariably exhibit noise across varying modalities and intensities. Hence, point cloud denoising (PCD) is essential as a preprocessing step to improve downstream task performance. Deep learning…

Accurate Point Cloud Registration (PCR) is an important task in 3D data processing, involving the estimation of a rigid transformation between two point clouds. While deep-learning methods have addressed key limitations of traditional…

Point cloud registration plays a critical role in a multitude of computer vision tasks, such as pose estimation and 3D localization. Recently, a plethora of deep learning methods were formulated that aim to tackle this problem. Most of…

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…

CTR prediction has been widely used in the real world. Many methods model feature interaction to improve their performance. However, most methods only learn a fixed representation for each feature without considering the varying importance…

In recent years, decentralized sensor networks have garnered significant attention in the field of state estimation owing to enhanced robustness, scalability, and fault tolerance. Optimal fusion performance can be achieved under fully…

Fingerprint dense registration aims to finely align fingerprint pairs at the pixel level, thereby reducing intra-class differences caused by distortion. Unfortunately, traditional methods exhibited subpar performance when dealing with…

3D anomaly detection in point-cloud data is critical for industrial quality control, aiming to identify structural defects with high reliability. However, current memory bank-based methods often suffer from inconsistent feature…

Point clouds obtained from 3D sensors are usually sparse. Existing methods mainly focus on upsampling sparse point clouds in a supervised manner by using dense ground truth point clouds. In this paper, we propose a self-supervised point…

In this paper we present SA-CNN, a hierarchical and lightweight self-attention based encoding and decoding architecture for representation learning of point cloud data. The proposed SA-CNN introduces convolution and transposed convolution…

How to extract significant point cloud features and estimate the pose between them remains a challenging question, due to the inherent lack of structure and ambiguous order permutation of point clouds. Despite significant improvements in…

Point cloud obtained from 3D scanning is often sparse, noisy, and irregular. To cope with these issues, recent studies have been separately conducted to densify, denoise, and complete inaccurate point cloud. In this paper, we advocate that…