Related papers: Context-Aware Transformer for 3D Point Cloud Autom…

In recent years, transformer structures have been widely applied in image captioning with impressive performance. For good captioning results, the geometry and position relations of different visual objects are often thought of as crucial…

Recent years have produced a variety of learning based methods in the context of computer vision and robotics. Most of the recently proposed methods are based on deep learning, which require very large amounts of data compared to…

We develop a novel approach for confidently accelerating inference in the large and expensive multilayer Transformers that are now ubiquitous in natural language processing (NLP). Amortized or approximate computational methods increase…

With the rise of large-scale models trained on broad data, in-context learning has become a new learning paradigm that has demonstrated significant potential in natural language processing and computer vision tasks. Meanwhile, in-context…

3D detection of traffic management objects, such as traffic lights and road signs, is vital for self-driving cars, particularly for address-to-address navigation where vehicles encounter numerous intersections with these static objects.…

Entropy modeling is a key component for high-performance image compression algorithms. Recent developments in autoregressive context modeling helped learning-based methods to surpass their classical counterparts. However, the performance of…

Active learning, a label-efficient paradigm, empowers models to interactively query an oracle for labeling new data. In the realm of LiDAR semantic segmentation, the challenges stem from the sheer volume of point clouds, rendering…

Center-aligned regression remains dominant in LiDAR-based 3D object detection, yet it suffers from fundamental instability: object centers often fall in sparse or empty regions of the bird's-eye-view (BEV) due to the front-surface-biased…

Self-attention modules have demonstrated remarkable capabilities in capturing long-range relationships and improving the performance of point cloud tasks. However, point cloud objects are typically characterized by complex, disordered, and…

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…

3D object detection is an essential vision technique for various robotic systems, such as augmented reality and domestic robots. Transformers as versatile network architectures have recently seen great success in 3D point cloud object…

This paper proposes an approach for rapid bounding box annotation for object detection datasets. The procedure consists of two stages: The first step is to annotate a part of the dataset manually, and the second step proposes annotations…

Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…

Cross-modal transfer learning is used to improve multi-modal classification models (e.g., for human activity recognition in human-robot collaboration). However, existing methods require paired sensor data at both training and inference,…

3D object pose estimation is a challenging task. Previous works always require thousands of object images with annotated poses for learning the 3D pose correspondence, which is laborious and time-consuming for labeling. In this paper, we…

3D object detection using LiDAR point clouds is a fundamental task in the fields of computer vision, robotics, and autonomous driving. However, existing 3D detectors heavily rely on annotated datasets, which are both time-consuming and…

As the development of 3D sensors, registration of 3D data (e.g. point cloud) coming from different kind of sensor is dispensable and shows great demanding. However, point cloud registration between different sensors is challenging because…

We show that off-the-shelf text-based Transformers, with no additional training, can perform few-shot in-context visual imitation learning, mapping visual observations to action sequences that emulate the demonstrator's behaviour. We…

A major bottleneck to scaling-up training of self-driving perception systems are the human annotations required for supervision. A promising alternative is to leverage "auto-labelling" offboard perception models that are trained to…

Promising performance has been achieved for visual perception on the point cloud. However, the current methods typically rely on labour-extensive annotations on the scene scans. In this paper, we explore how synthetic models alleviate the…