Related papers: Rotation-Invariant Transformer for Point Cloud Mat…

Leveraging prior knowledge on intraclass variance due to transformations is a powerful method to improve the sample complexity of deep neural networks. This makes them applicable to practically important use-cases where training data is…

Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Existing approaches emphasize semantic awareness by enforcing feature consistency across…

DIFF Transformer addresses the issue of irrelevant context interference by introducing a differential attention mechanism that enhances the robustness of local attention. However, it has two critical limitations: the lack of global context…

Point cloud registration methods can effectively handle large-scale, partially overlapping point cloud pairs. Despite its practicality, matching the unbalanced pairs in terms of spatial extent and density has been overlooked and rarely…

Low-overlap point cloud registration (PCR) remains a significant challenge in 3D vision. Traditional evaluation metrics, such as Maximum Inlier Count, become ineffective under extremely low inlier ratios. In this paper, we revisit the…

Implicit neural networks have emerged as a crucial technology in 3D surface reconstruction. To reconstruct continuous surfaces from discrete point clouds, encoding the input points into regular grid features (plane or volume) has been…

Performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Many image classification tasks, such as those related to cellular imaging, exhibit invariance to rotation. We present a novel…

Transformer, as an alternative to CNN, has been proven effective in many modalities (e.g., texts and images). For 3D point cloud transformers, existing efforts focus primarily on pushing their accuracy to the state-of-the-art level.…

We propose an intra frame predictive strategy for compression of 3D point cloud attributes. Our approach is integrated with the region adaptive graph Fourier transform (RAGFT), a multi-resolution transform formed by a composition of…

We propose a methodology for robust, real-time place recognition using an imaging lidar, which yields image-quality high-resolution 3D point clouds. Utilizing the intensity readings of an imaging lidar, we project the point cloud and obtain…

Radar-based indoor 3D human pose estimation typically relied on fine-grained 3D keypoint labels, which are costly to obtain especially in complex indoor settings involving clutter, occlusions, or multiple people. In this paper, we propose…

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…

Transformers have been at the heart of the Natural Language Processing (NLP) and Computer Vision (CV) revolutions. The significant success in NLP and CV inspired exploring the use of Transformers in point cloud processing. However, how do…

We propose octree-based transformers, named OctFormer, for 3D point cloud learning. OctFormer can not only serve as a general and effective backbone for 3D point cloud segmentation and object detection but also have linear complexity and is…

Point Cloud Registration (PCR) estimates the relative rigid transformation between two point clouds of the same scene. Despite significant progress with learning-based approaches, existing methods still face challenges when the overlapping…

3D point cloud is an efficient and flexible representation of 3D structures. Recently, neural networks operating on point clouds have shown superior performance on 3D understanding tasks such as shape classification and part segmentation.…

Inspired by recent advances in vision transformers for object detection, we propose Li3DeTr, an end-to-end LiDAR based 3D Detection Transformer for autonomous driving, that inputs LiDAR point clouds and regresses 3D bounding boxes. The…

Humans and animals recognize objects irrespective of the beholder's point of view, which may drastically change their appearances. Artificial pattern recognizers also strive to achieve this, e.g., through translational invariance in…

Point cloud models with neural network architectures have achieved great success and have been widely used in safety-critical applications, such as Lidar-based recognition systems in autonomous vehicles. However, such models are shown…

In recent years, deep-learning-based point cloud registration methods have shown significant promise. Furthermore, learning-based 3D detectors have demonstrated their effectiveness in encoding semantic information from LiDAR data. In this…