Related papers: Self-Supervised Cross-Modal Learning for Image-to-…

Semantic segmentation of large-scale 3D point clouds is crucial for applications such as autonomous driving and urban digital twins. However, the sparse sampling pattern of LiDAR and the view-dependent geometric distortion in image…

Enhancing AI systems to perform tasks following human instructions can significantly boost productivity. In this paper, we present InstructP2P, an end-to-end framework for 3D shape editing on point clouds, guided by high-level textual…

Self-supervised learning of point cloud aims to leverage unlabeled 3D data to learn meaningful representations without reliance on manual annotations. However, current approaches face challenges such as limited data diversity and inadequate…

Recently, a growing number of work design unsupervised paradigms for point cloud processing to alleviate the limitation of expensive manual annotation and poor transferability of supervised methods. Among them, CrossPoint follows the…

The recent multi-modality models have achieved great performance in many vision tasks because the extracted features contain the multi-modality knowledge. However, most of the current registration descriptors have only concentrated on local…

Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly…

3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial correspondences, and it's even harder in the absence of any initial estimation…

Pretraining on large labeled datasets is a prerequisite to achieve good performance in many computer vision tasks like 2D object recognition, video classification etc. However, pretraining is not widely used for 3D recognition tasks where…

3D dense captioning aims to describe individual objects by natural language in 3D scenes, where 3D scenes are usually represented as RGB-D scans or point clouds. However, only exploiting single modal information, e.g., point cloud, previous…

3D point cloud registration is a fundamental task in robotics and computer vision. Recently, many learning-based point cloud registration methods based on correspondences have emerged. However, these methods heavily rely on such…

An effective framework for learning 3D representations for perception tasks is distilling rich self-supervised image features via contrastive learning. However, image-to point representation learning for autonomous driving datasets faces…

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…

Point clouds, as a primary representation of 3D data, can be categorized into scene domain point clouds and object domain point clouds. Point cloud self-supervised learning (SSL) has become a mainstream paradigm for learning 3D…

We tackle the problem of localizing 3D point cloud submaps using complex and diverse natural language descriptions, and present Text2Loc++, a novel neural network designed for effective cross-modal alignment between language and point…

Global registration of point clouds aims to find an optimal alignment of a sequence of 2D or 3D point sets. In this paper, we present a novel method that takes advantage of current deep learning techniques for unsupervised learning of…

Current point cloud registration methods are mainly based on local geometric information and usually ignore the semantic information contained in the scenes. In this paper, we treat the point cloud registration problem as a semantic…

Point cloud registration is a key task in many computational fields. Previous correspondence matching based methods require the inputs to have distinctive geometric structures to fit a 3D rigid transformation according to point-wise sparse…

Transfer learning has long been a key factor in the advancement of many fields including 2D image analysis. Unfortunately, its applicability in 3D data processing has been relatively limited. While several approaches for point cloud…

Multi-modal methods based on camera and LiDAR sensors have garnered significant attention in the field of 3D detection. However, many prevalent works focus on single or partial stage fusion, leading to insufficient feature extraction and…

Current 3D self-supervised learning methods of 3D scenes face a data desert issue, resulting from the time-consuming and expensive collecting process of 3D scene data. Conversely, 3D shape datasets are easier to collect. Despite this,…