相关论文: A deep perceptual metric for 3D point clouds

Point clouds analysis has grasped researchers' eyes in recent years, while 3D semantic segmentation remains a problem. Most deep point clouds models directly conduct learning on 3D point clouds, which will suffer from the severe sparsity…

With the development of the 3D data acquisition facilities, the increasing scale of acquired 3D point clouds poses a challenge to the existing data compression techniques. Although promising performance has been achieved in static point…

With the rapid progress of deep convolutional neural networks, in almost all robotic applications, the availability of 3D point clouds improves the accuracy of 3D semantic segmentation methods. Rendering of these irregular, unstructured,…

The purpose of intrinsic decomposition is to separate an image into its albedo (reflective properties) and shading components (illumination properties). This is challenging because it's an ill-posed problem. Conventional approaches…

Learning implicit representations has been a widely used solution for surface reconstruction from 3D point clouds. The latest methods infer a distance or occupancy field by overfitting a neural network on a single point cloud. However,…

Differentiable rendering is a very successful technique that applies to a Single-View 3D Reconstruction. Current renderers use losses based on pixels between a rendered image of some 3D reconstructed object and ground-truth images from…

Deep learning within the context of point clouds has gained much research interest in recent years mostly due to the promising results that have been achieved on a number of challenging benchmarks, such as 3D shape recognition and scene…

Current 3D object detection methods are heavily influenced by 2D detectors. In order to leverage architectures in 2D detectors, they often convert 3D point clouds to regular grids (i.e., to voxel grids or to bird's eye view images), or rely…

Medical image analysis using deep learning has recently been prevalent, showing great performance for various downstream tasks including medical image segmentation and its sibling, volumetric image segmentation. Particularly, a typical…

The remarkable breakthroughs in point cloud representation learning have boosted their usage in real-world applications such as self-driving cars and virtual reality. However, these applications usually have an urgent requirement for not…

3D object detection is still an open problem in autonomous driving scenes. When recognizing and localizing key objects from sparse 3D inputs, autonomous vehicles suffer from a larger continuous searching space and higher fore-background…

Convolution on 3D point clouds that generalized from 2D grid-like domains is widely researched yet far from perfect. The standard convolution characterises feature correspondences indistinguishably among 3D points, presenting an intrinsic…

3D reconstruction from images is a core problem in computer vision. With recent advances in deep learning, it has become possible to recover plausible 3D shapes even from single RGB images for the first time. However, obtaining detailed…

To help bridge the gap between internet vision-style problems and the goal of vision for embodied perception we instantiate a large-scale navigation task -- Embodied Question Answering [1] in photo-realistic environments (Matterport 3D). We…

We propose a practical deep generative approach for lossless point cloud geometry compression, called MSVoxelDNN, and show that it significantly reduces the rate compared to the MPEG G-PCC codec. Our previous work based on autoregressive…

Point cloud patterns are hard to learn because of the implicit local geometry features among the orderless points. In recent years, point cloud representation in 2D space has attracted increasing research interest since it exposes the local…

In this paper, we investigate the combination of voxel-based methods and point-based methods, and propose a novel end-to-end two-stage 3D object detector named SGNet for point clouds scenes. The voxel-based methods voxelize the scene to…

Point cloud data is pivotal in applications like autonomous driving, virtual reality, and robotics. However, its substantial volume poses significant challenges in storage and transmission. In order to obtain a high compression ratio,…

In the field of autonomous driving, a variety of sensor data types exist, each representing different modalities of the same scene. Therefore, it is feasible to utilize data from other sensors to facilitate image compression. However, few…

In this paper we propose a rotation-invariant deep network for point clouds analysis. Point-based deep networks are commonly designed to recognize roughly aligned 3D shapes based on point coordinates, but suffer from performance drops with…