相关论文: Representing 3D sparse map points and lines for ca…

Visual Place Recognition is an essential component of systems for camera localization and loop closure detection, and it has attracted widespread interest in multiple domains such as computer vision, robotics and AR/VR. In this work, we…

Camera relocalization is the key component of simultaneous localization and mapping (SLAM) systems. This paper proposes a learning-based approach, named Sparse Spatial Scene Embedding with Graph Neural Networks (S3E-GNN), as an end-to-end…

Accurate registration of 2D imagery with point clouds is a key technology for image-LiDAR point cloud fusion, camera to laser scanner calibration and camera localization. Despite continuous improvements, automatic registration of 2D and 3D…

LiDAR mapping is important yet challenging in self-driving and mobile robotics. To tackle such a global point cloud registration problem, DeepMapping converts the complex map estimation into a self-supervised training of simple deep…

3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information. Conventional 2D convolutions are unsuitable for this task because they fail to capture local object and its scale…

Feature matching plays a fundamental role in many computer vision tasks, yet existing methods heavily rely on scarce and clean multi-view image collections, which constrains their generalization to diverse and challenging scenarios.…

Deep learning and convolutional neural networks (ConvNets) have been successfully applied to most relevant tasks in the computer vision community. However, these networks are computationally demanding and not suitable for embedded devices…

Camera localization is a classical computer vision task that serves various Artificial Intelligence and Robotics applications. With the rapid developments of Deep Neural Networks (DNNs), end-to-end visual localization methods are prosperous…

Robust and efficient local feature matching plays a crucial role in applications such as SLAM and visual localization for robotics. Despite great progress, it is still very challenging to extract robust and discriminative visual features in…

Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods. The commonly occurred misalignment comes from the facts that the mapping from…

With the rapid advancement of technology, 3D data acquisition and utilization have become increasingly prevalent across various fields, including computer vision, robotics, and geospatial analysis. 3D data, captured through methods such as…

Most of the state-of-the-art indirect visual SLAM methods are based on the sparse point features. However, it is hard to find enough reliable point features for state estimation in the case of low-textured scenes. Line features are abundant…

Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data. The best-performing models for single-image 2D-3D lifting use graph convolutional networks (GCNs) that typically…

Current state-of-the-art solutions for motion capture from a single camera are optimization driven: they optimize the parameters of a 3D human model so that its re-projection matches measurements in the video (e.g. person segmentation,…

Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation. Unlike classical optimization-based methods, recent learning-based methods leverage the power of deep learning for…

The integration of neural rendering and the SLAM system recently showed promising results in joint localization and photorealistic view reconstruction. However, existing methods, fully relying on implicit representations, are so…

Place recognition plays an essential role in the field of autonomous driving and robot navigation. Point cloud based methods mainly focus on extracting global descriptors from local features of point clouds. Despite having achieved…

Point cloud based place recognition is still an open issue due to the difficulty in extracting local features from the raw 3D point cloud and generating the global descriptor, and it's even harder in the large-scale dynamic environments. In…

Self-supervised learning on point clouds has gained a lot of attention recently, since it addresses the label-efficiency and domain-gap problems on point cloud tasks. In this paper, we propose a novel self-supervised framework to learn…

Multimodal 3D grounding has garnered considerable interest in Vision-Language Models (VLMs) \cite{yin2025spatial} for advancing spatial reasoning in complex environments. However, these models suffer from a severe "2D semantic bias" that…