Related papers: DBQ-SSD: Dynamic Ball Query for Efficient 3D Objec…

Incremental object detection (IOD) aims to sequentially learn new classes, while maintaining the capability to locate and identify old ones. As the training data arrives with annotations only with new classes, IOD suffers from catastrophic…

Features from multiple scales can greatly benefit the semantic edge detection task if they are well fused. However, the prevalent semantic edge detection methods apply a fixed weight fusion strategy where images with different semantics are…

Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained…

In reinforcement learning, it is often difficult to automate high-dimensional, rapid decision-making in dynamic environments, especially when domains require real-time online interaction and adaptive strategies such as web-based games. This…

Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional…

In this work we propose 3D-FFS, a novel approach to make sensor fusion based 3D object detection networks significantly faster using a class of computationally inexpensive heuristics. Existing sensor fusion based networks generate 3D region…

LiDAR point clouds are widely used in autonomous driving and consist of large numbers of 3D points captured at high frequency to represent surrounding objects such as vehicles, pedestrians, and traffic signs. While this dense data enables…

Deep Q-learning Network (DQN) is a successful way which combines reinforcement learning with deep neural networks and leads to a widespread application of reinforcement learning. One challenging problem when applying DQN or other…

The task of detecting 3D objects is important to various robotic applications. The existing deep learning-based detection techniques have achieved impressive performance. However, these techniques are limited to run with a graphics…

Diffusion Transformer (DiT), an emerging diffusion model for image generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs stem from the static inference…

3D vehicle detection based on multi-modal fusion is an important task of many applications such as autonomous driving. Although significant progress has been made, we still observe two aspects that need to be further improvement: First, the…

Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense…

We introduce a novel superpoint-based transformer architecture for efficient semantic segmentation of large-scale 3D scenes. Our method incorporates a fast algorithm to partition point clouds into a hierarchical superpoint structure, which…

We present a new 3D point-based detector model, named Shift-SSD, for precise 3D object detection in autonomous driving. Traditional point-based 3D object detectors often employ architectures that rely on a progressive downsampling of…

In this work, we present a novel Sports Ball Detection and Tracking (SBDT) method that can be applied to various sports categories. Our approach is composed of (1) high-resolution feature extraction, (2) position-aware model training, and…

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion…

We present SKD, a novel keypoint detector that uses saliency to determine the best candidates from a point cloud for tasks such as registration and reconstruction. The approach can be applied to any differentiable deep learning descriptor…

To boost a detector for single-frame 3D object detection, we present a new approach to train it to simulate features and responses following a detector trained on multi-frame point clouds. Our approach needs multi-frame point clouds only…

Deep neural networks have revolutionized 3D point cloud processing, yet efficiently handling large and irregular point clouds remains challenging. To tackle this problem, we introduce FastPoint, a novel software-based acceleration technique…

This paper presents a new methodology to alleviate the fundamental trade-off between accuracy and latency in spiking neural networks (SNNs). The approach involves decoding confidence information over time from the SNN outputs and using it…