Related papers: OctFormer: Octree-based Transformers for 3D Point …

Most existing methods realize 3D instance segmentation by extending those models used for 3D object detection or 3D semantic segmentation. However, these non-straightforward methods suffer from two drawbacks: 1) Imprecise bounding boxes or…

Designing an efficient yet deployment-friendly 3D backbone to handle sparse point clouds is a fundamental problem in 3D perception. Compared with the customized sparse convolution, the attention mechanism in Transformers is more appropriate…

Point cloud is point sets defined in 3D metric space. Point cloud has become one of the most significant data format for 3D representation. Its gaining increased popularity as a result of increased availability of acquisition devices, such…

Transformers have excelled in many tasks including vision. However, efficient deployment of transformer models in low-latency or high-throughput applications is hindered by the computation in the attention mechanism which involves expensive…

Accurate and computationally efficient 3D medical image segmentation remains a critical challenge in clinical workflows. Transformer-based architectures often demonstrate superior global contextual modeling but at the expense of excessive…

Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale LiDAR registration methods has been rarely explored before. Challenges mainly arise from the huge point scale, complex point…

3D shape recognition has attracted more and more attention as a task of 3D vision research. The proliferation of 3D data encourages various deep learning methods based on 3D data. Now there have been many deep learning models based on…

Environment perception including detection, classification, tracking, and motion prediction are key enablers for automated driving systems and intelligent transportation applications. Fueled by the advances in sensing technologies and…

In this paper, we propose a simple attention mechanism, we call box-attention. It enables spatial interaction between grid features, as sampled from boxes of interest, and improves the learning capability of transformers for several vision…

For current object detectors, the scale of the receptive field of feature extraction operators usually increases layer by layer. Those operators are called scale-oriented operators in this paper, such as the convolution layer in CNN, and…

Point cloud processing methods leverage local and global point features %at the feature level to cater to downstream tasks, yet they often overlook the task-level context inherent in point clouds during the encoding stage. We argue that…

3D point cloud perception remains tightly coupled to custom CUDA operators for spatial operations, limiting portability and efficiency on non-NVIDIA, AMD, and embedded hardware. We introduce PointTransformerX (PTX), a fully PyTorch-native…

Octree-based context learning has recently become a leading method in point cloud compression. However, its potential on lossy compression remains undiscovered. The traditional lossy compression paradigm using lossless octree representation…

The field of 3D object detection from point clouds is rapidly advancing in computer vision, aiming to accurately and efficiently detect and localize objects in three-dimensional space. Current 3D detectors commonly fall short in terms of…

Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical…

Existing point cloud based 3D detectors are designed for the particular scene, either indoor or outdoor ones. Because of the substantial differences in object distribution and point density within point clouds collected from various…

The application of deep learning to 3D point clouds is challenging due to its lack of order. Inspired by the point embeddings of PointNet and the edge embeddings of DGCNNs, we propose three improvements to the task of point cloud analysis.…

This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming…

Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial instance masks in the first cross-attention, and then iteratively…

Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics. As a dominating technique in AI, deep learning has been successfully used…