Related papers: Voxel Set Transformer: A Set-to-Set Approach to 3D…

This paper tackles the high computational/space complexity associated with Multi-Head Self-Attention (MHSA) in vanilla vision transformers. To this end, we propose Hierarchical MHSA (H-MHSA), a novel approach that computes self-attention in…

Transformers have gained much attention by outperforming convolutional neural networks in many 2D vision tasks. However, they are known to have generalization problems and rely on massive-scale pre-training and sophisticated training…

This paper presents ViewFormer, a simple yet effective model for multi-view 3d shape recognition and retrieval. We systematically investigate the existing methods for aggregating multi-view information and propose a novel ``view set"…

We present a unified, efficient and effective framework for point-cloud based 3D object detection. Our two-stage approach utilizes both voxel representation and raw point cloud data to exploit respective advantages. The first stage network,…

Object detection in point cloud data is one of the key components in computer vision systems, especially for autonomous driving applications. In this work, we present Voxel-FPN, a novel one-stage 3D object detector that utilizes raw data…

In this paper, we propose a two-stage deep learning framework called VoxelContext-Net for both static and dynamic point cloud compression. Taking advantages of both octree based methods and voxel based schemes, our approach employs the…

Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequence modeling capabilities. However, conventional…

Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers…

Recent work on 3D object detection advocates point cloud voxelization in birds-eye view, where objects preserve their physical dimensions and are naturally separable. When represented in this view, however, point clouds are sparse and have…

We introduce PointConvFormer, a novel building block for point cloud based deep network architectures. Inspired by generalization theory, PointConvFormer combines ideas from point convolution, where filter weights are only based on relative…

Most modern deep learning-based multi-view 3D reconstruction techniques use RNNs or fusion modules to combine information from multiple images after independently encoding them. These two separate steps have loose connections and do not…

Motivated by the increasing popularity of attention mechanisms, we observe that popular convolutional (conv.) attention models like Squeeze-and-Excite (SE) and Convolutional Block Attention Module (CBAM) rely on expensive multi-layer…

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…

Transformers exhibit great advantages in handling computer vision tasks. They model image classification tasks by utilizing a multi-head attention mechanism to process a series of patches consisting of split images. However, for complex…

Although accurate and fast point cloud classification is a fundamental task in 3D applications, it is difficult to achieve this purpose due to the irregularity and disorder of point clouds that make it challenging to achieve effective and…

Point cloud segmentation, which helps us understand the environment of specific structures and objects, can be performed in class-specific and class-agnostic ways. We propose a novel region-based transformer model called Region-Transformer…

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…

Dexterous manipulation enables complex tasks but suffers from self-occlusion, severe depth noise, and depth information loss when manipulating transparent objects. To solve this problem, this paper proposes TransDex, a 3D visuo-tactile…

Modern neural architectures for 3D point cloud processing contain both convolutional layers and attention blocks, but the best way to assemble them remains unclear. We analyse the role of different computational blocks in 3D point cloud…

We present ASSET, a neural architecture for automatically modifying an input high-resolution image according to a user's edits on its semantic segmentation map. Our architecture is based on a transformer with a novel attention mechanism.…