相关论文: Flash3D: Super-scaling Point Transformers through …

While recent feed-forward 3D reconstruction models accelerate 3D reconstruction by jointly inferring dense geometry and camera poses in a single pass, their reliance on dense attention imposes a quadratic complexity, creating a prohibitive…

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…

LiDAR-based 3D detection has made great progress in recent years. However, the performance of 3D detectors is considerably limited when deployed in unseen environments, owing to the severe domain gap problem. Existing domain adaptive 3D…

General point clouds have been increasingly investigated for different tasks, and recently Transformer-based networks are proposed for point cloud analysis. However, there are barely related works for medical point clouds, which are…

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM…

Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both…

In this paper, we present Position-to-Structure Attention Transformers (PS-Former), a Transformer-based algorithm for 3D point cloud recognition. PS-Former deals with the challenge in 3D point cloud representation where points are not…

As the foundation of large language models (LLMs), self-attention module faces the challenge of quadratic time and memory complexity with respect to sequence length. FlashAttention accelerates attention computation and reduces its memory…

Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds. Despite a plethora of learning-based 2D or 3D local feature descriptors and detectors having been proposed,…

Given the rapid development of 3D scanners, point clouds are becoming popular in AI-driven machines. However, point cloud data is inherently sparse and irregular, causing significant difficulties for machine perception. In this work, we…

Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors. Previous works…

This paper presents an accurate and fast 3D global localization method, 3D-BBS, that extends the existing branch-and-bound (BnB)-based 2D scan matching (BBS) algorithm. To reduce memory consumption, we utilize a sparse hash table for…

3D morphable models are widely used for the shape representation of an object class in computer vision and graphics applications. In this work, we focus on deep 3D morphable models that directly apply deep learning on 3D mesh data with a…

We tackle the problem of object-centric learning on point clouds, which is crucial for high-level relational reasoning and scalable machine intelligence. In particular, we introduce a framework, SPAIR3D, to factorize a 3D point cloud into a…

Transformer are widely used in various fields such as natural language processing and computer vision. However, the training time for large Transformer models can be challenging due to the Multi-Head Attention (MHA) mechanism. Especially as…

3D single object tracking is a key issue for robotics. In this paper, we propose a transformer module called Point-Track-Transformer (PTT) for point cloud-based 3D single object tracking. PTT module contains three blocks for feature…

SSF3D modified the semi-supervised 3D object detection (SS3DOD) framework, which designed specifically for point cloud data. Leveraging the characteristics of non-coincidence and weak correlation of target objects in point cloud, we adopt a…

The computational cost of softmax-based attention in transformers limits their applicability to long-context tasks. Adaptive sparsity, of which $\alpha$-entmax attention is an example, offers a flexible data-dependent alternative, but…

Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…