Related papers: CenterFormer: Center-based Transformer for 3D Obje…

Cell detection in microscopy images is important to study how cells move and interact with their environment. Most recent deep learning-based methods for cell detection use convolutional neural networks (CNNs). However, inspired by the…

Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector, followed by different temporal aggregation…

Object detection with Transformers (DETR) has achieved a competitive performance over traditional detectors, such as Faster R-CNN. However, the potential of DETR remains largely unexplored for the more challenging task of arbitrary-oriented…

Recently, 3D shape understanding has achieved significant progress due to the advances of deep learning models on various data formats like images, voxels, and point clouds. Among them, point clouds and multi-view images are two…

Transfomer-based approaches advance the recent development of multi-camera 3D detection both in academia and industry. In a vanilla transformer architecture, queries are randomly initialised and optimised for the whole dataset, without…

Reliable perception is essential for autonomous driving systems to operate safely under diverse real-world traffic conditions. However, camera- and LiDAR-based perception systems suffer from performance degradation under adverse weather and…

Multi-camera-based 3D object detection has made notable progress in the past several years. However, we observe that there are cases (e.g. faraway regions) in which popular 2D object detectors are more reliable than state-of-the-art 3D…

Lidars and cameras play essential roles in autonomous driving, offering complementary information for 3D detection. The state-of-the-art fusion methods integrate them at the feature level, but they mostly rely on the learned soft…

Keypoint-based detectors have achieved pretty-well performance. However, incorrect keypoint matching is still widespread and greatly affects the performance of the detector. In this paper, we propose CentripetalNet which uses centripetal…

Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully…

Transformer-based methods have become the dominant approach for 3D instance segmentation. These methods predict instance masks via instance queries, ranking them by classification confidence and IoU scores to select the top prediction as…

While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention, but ignore their content and fail to establish relationships…

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…

3D object detection with surround-view images is an essential task for autonomous driving. In this work, we propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in…

3D object detection plays an important role in a large number of real-world applications. It requires us to estimate the localizations and the orientations of 3D objects in real scenes. In this paper, we present a new network architecture…

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…

Transformer-based models have significantly advanced natural language processing and computer vision in recent years. However, due to the irregular and disordered structure of point cloud data, transformer-based models for 3D deep learning…

There are two mainstreams for object detection: top-down and bottom-up. The state-of-the-art approaches mostly belong to the first category. In this paper, we demonstrate that the bottom-up approaches are as competitive as the top-down and…

We present a novel architecture for 3D object detection, M3DeTR, which combines different point cloud representations (raw, voxels, bird-eye view) with different feature scales based on multi-scale feature pyramids. M3DeTR is the first…