Related papers: Text2Loc++: Generalizing 3D Point Cloud Localizati…

Existing point cloud feature learning networks often incorporate sequences of sampling, neighborhood grouping, neighborhood-wise feature learning, and feature aggregation to learn high-semantic point features that represent the global…

The emergence of Multimodal Large Language Models (MLLMs) has revolutionized image understanding by bridging textual and visual modalities. However, these models often struggle with capturing fine-grained semantic information, such as the…

3D point cloud interpretation is a challenging task due to the randomness and sparsity of the component points. Many of the recently proposed methods like PointNet and PointCNN have been focusing on learning shape descriptions from point…

Understanding 3D point clouds through language remains a fundamental challenge in computer graphics and visual computing, due to the irregular structure of point cloud data and the lack of explicit reasoning in existing 3D multimodal…

Effectively representing 3D scenes for Multimodal Large Language Models (MLLMs) is crucial yet challenging. Existing approaches commonly only rely on 2D image features and use varied tokenization approaches. This work presents a rigorous…

3D vehicle detection based on point cloud is a challenging task in real-world applications such as autonomous driving. Despite significant progress has been made, we observe two aspects to be further improved. First, the semantic context…

This paper addresses the problem of 3D referring expression comprehension (REC) in autonomous driving scenario, which aims to ground a natural language to the targeted region in LiDAR point clouds. Previous approaches for REC usually focus…

Point cloud completion aims to recover complete 3D geometry from partial observations caused by limited viewpoints and occlusions. Existing learning-based works, including 3D Convolutional Neural Network (CNN)-based, point-based, and…

Embodied outdoor scene understanding forms the foundation for autonomous agents to perceive, analyze, and react to dynamic driving environments. However, existing 3D understanding is predominantly based on 2D Vision-Language Models (VLMs),…

Traditional 3D scene understanding techniques are generally predicated on hand-annotated label sets, but in recent years a new class of open-vocabulary 3D scene understanding techniques has emerged. Despite the success of this paradigm on…

We study an important, yet largely unexplored problem of large-scale cross-modal visual localization by matching ground RGB images to a geo-referenced aerial LIDAR 3D point cloud (rendered as depth images). Prior works were demonstrated on…

Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging. In this paper, we propose a new model, named InstanceRefer, to achieve a superior 3D visual grounding…

Text spotting in natural scene images is of great importance for many image understanding tasks. It includes two sub-tasks: text detection and recognition. In this work, we propose a unified network that simultaneously localizes and…

In this paper, we present a comprehensive point cloud semantic segmentation network that aggregates both local and global multi-scale information. First, we propose an Angle Correlation Point Convolution (ACPConv) module to effectively…

Learning discriminative shape representation directly on point clouds is still challenging in 3D shape analysis and understanding. Recent studies usually involve three steps: first splitting a point cloud into some local regions, then…

Unlike its image based counterpart, point cloud based retrieval for place recognition has remained as an unexplored and unsolved problem. This is largely due to the difficulty in extracting local feature descriptors from a point cloud that…

Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions,…

Existing position based point cloud filtering methods can hardly preserve sharp geometric features. In this paper, we rethink point cloud filtering from a non-learning non-local non-normal perspective, and propose a novel position based…

Point cloud based retrieval for place recognition is still a challenging problem due to drastic appearance and illumination changes of scenes in changing environments. Existing deep learning based global descriptors for the retrieval task…

In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map. Compared to RGB…