Related papers: ACL-SPC: Adaptive Closed-Loop system for Self-Supe…
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…
This paper studies Semi-Supervised Domain Adaptation (SSDA), a practical yet under-investigated research topic that aims to learn a model of good performance using unlabeled samples and a few labeled samples in the target domain, with the…
The problems of shape classification and part segmentation from 3D point clouds have garnered increasing attention in the last few years. Both of these problems, however, suffer from relatively small training sets, creating the need for…
Training deep learning models for point cloud prediction tasks such as shape completion and generation depends critically on loss functions that measure discrepancies between predicted and ground-truth point sets. Commonly used functions…
In this work, we propose to learn local descriptors for point clouds in a self-supervised manner. In each iteration of the training, the input of the network is merely one unlabeled point cloud. On top of our previous work, that directly…
A supervised learning framework is proposed to approximate a model predictive controller (MPC) with reduced computational complexity and guarantees on stability and constraint satisfaction. The framework can be used for a wide class of…
For a long time, the point cloud completion task has been regarded as a pure generation task. After obtaining the global shape code through the encoder, a complete point cloud is generated using the shape priorly learnt by the networks.…
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…
Recent advances in point cloud In-Context Learning (ICL) have demonstrated strong multitask capabilities. Existing approaches typically adopt a Masked Point Modeling (MPM)-based paradigm for point cloud ICL. However, MPM-based methods…
The rapid growth of the digital economy and artificial intelligence has transformed cloud data centers into essential infrastructure with substantial energy consumption and carbon emission, necessitating effective energy management.…
Great progress has been made in point cloud classification with learning-based methods. However, complex scene and sensor inaccuracy in real-world application make point cloud data suffer from corruptions, such as occlusion, noise and…
Deep neural networks have achieved promising performance in supervised point cloud applications, but manual annotation is extremely expensive and time-consuming in supervised learning schemes. Unsupervised domain adaptation (UDA) addresses…
Test-Time Training (TTT) has emerged as a promising solution to address distribution shifts in 3D point cloud classification. However, existing methods often rely on computationally expensive backpropagation during adaptation, limiting…
We propose a novel active learning framework for multi-view semantic segmentation. This framework relies on a new score that measures the discrepancy between point cloud distributions generated from the extra geometrical information derived…
Self-supervised learning has recently achieved great success in representation learning without human annotations. The dominant method -- that is contrastive learning, is generally based on instance discrimination tasks, i.e., individual…
In this paper, we present a comprehensive point cloud semantic segmentation network that aggregates both local and global multi-scale information. First, we propose an Angle Correlation Point Convolution (ACPConv) module to effectively…
Recent years have witnessed the growth of point cloud based applications because of its realistic and fine-grained representation of 3D objects and scenes. However, it is a challenging problem to compress sparse, unstructured, and…
Point clouds collected from real-world environments are often incomplete due to factors such as limited sensor resolution, single viewpoints, occlusions, and noise. These challenges make point cloud completion essential for various…
Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors. Existing top-down approaches tackle this problem by either…
This paper presents PCDreamer, a novel method for point cloud completion. Traditional methods typically extract features from partial point clouds to predict missing regions, but the large solution space often leads to unsatisfactory…