11 accepted papers
The sparse unordered structure of point clouds causes unnecessary computation and energy consumption in deep models. Conventionally, the Transformer architecture is leveraged to model global relationships in point clouds, however, its quadratic complexity restricts scalability. Although the Mamba a…
The inherent sparsity, lack of structure, and rotation sensitivity of point clouds often lead to high computational and parameter cost in robust feature learning. To address these problems, we present QPoint, a lightweight framework that leverages robust quaternion feature learning. QPoint incorpora…
The unordered nature of point cloud data poses significant challenges to conventional architectures primarily designed for structured data. Spiking neural networks (SNN), by virtue of their inherent sparsity and dynamics, are particularly well-suited for processing point clouds to effectively extrac…
Spiking neural networks (SNNs), inspired by the inherent spiking computation paradigm of the biological neural systems, have exhibited superior energy efficiency in 2D classification tasks over traditional artificial neural networks (ANNs). However, the regression potential of SNNs has not been well…
The objective of 3D single object tracking is to determine the location of a target in a series of point clouds. However, this task still faces several challenges, such as the sparsity of the point cloud and the timeliness requirement of models. In this letter, we propose using an iterative siamese
Spiking neural networks (SNNs) have revolutionized neural learning and are making remarkable strides in image analysis and robot control tasks with ultra-low power consumption advantages. Inspired by this success, we investigate the application of spiking neural networks to 3D point cloud processing…
3D single object tracking is the task of localizing a target object in a search point cloud frame. In this letter, we present a multi-level structure-enhanced tracking model to improve the tracking performance in sparse 3D point clouds. Towards this end, we first encode the target and the search poi
We present a novel approach for image-goal navigation, where an agent navigates with a goal image rather than accurate target information, which is more challenging. Our goal is to decouple the learning of navigation goal planning, collision avoidance, and navigation ending prediction, which enables
To enhance the cross-target and cross-scene generalization of target-driven visual navigation based on deep reinforcement learning (RL), we introduce an information-theoretic regularization term into the RL objective. The regularization maximizes the mutual information between navigation actions and
Scene reconstruction with consumer-level RGB-D cameras has developed considerable momentum in both robotics and vision communities. In the literature of robotics, high-quality camera tracking, the key to accurate reconstruction, is challenging in geometric featureless scenes or under large lighting
We present a target-driven navigation system to improve mapless visual navigation in indoor scenes. Our method takes a multi-view observation of a robot and a target image as inputs at each time step to provide a sequence of actions that move the robot to the target without relying on odometry or GP