Related papers: Juggling With Representations: On the Information …

LiDAR and camera are two modalities available for 3D semantic segmentation in autonomous driving. The popular LiDAR-only methods severely suffer from inferior segmentation on small and distant objects due to insufficient laser points, while…

Point cloud segmentation is a fundamental task in 3D vision that serves a wide range of applications. Although great progresses have been made these years, its practical usability is still limited by the availability of training data.…

Existing text-driven infrared and visible image fusion approaches often rely on textual information at the sentence level, which can lead to semantic noise from redundant text and fail to fully exploit the deeper semantic value of textual…

Multimodal representation learning produces high-dimensional embeddings that align diverse modalities in a shared latent space. While this enables strong generalization, it also introduces scalability challenges, both in terms of storage…

Seamless integration of virtual and physical worlds in augmented reality benefits from the system semantically "understanding" the physical environment. AR research has long focused on the potential of context awareness, demonstrating novel…

Current point cloud registration methods are mainly based on local geometric information and usually ignore the semantic information contained in the scenes. In this paper, we treat the point cloud registration problem as a semantic…

Point-based representations have consistently played a vital role in geometric data structures. Most point cloud learning and processing methods typically leverage the unordered and unconstrained nature to represent the underlying geometry…

A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud…

Effectively summarizing dense 3D point cloud data and extracting motion information of moving objects (moving object segmentation, MOS) is crucial to autonomous driving and robotics applications. How to effectively utilize motion and…

Multimodal datasets contain an enormous amount of relational information, which grows exponentially with the introduction of new modalities. Learning representations in such a scenario is inherently complex due to the presence of multiple…

Reliable 3D segmentation is critical for understanding complex scenes with dense layouts and multi-scale objects, as commonly seen in industrial environments. In such scenarios, heavy occlusion weakens geometric boundaries between objects,…

This work proposes a general-purpose, fully-convolutional network architecture for efficiently processing large-scale 3D data. One striking characteristic of our approach is its ability to process unorganized 3D representations such as…

Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. This is challenging due to the difficulty of combining multi-granularity geometric and semantic features…

Elevation maps are commonly used to represent the environment of mobile robots and are instrumental for locomotion and navigation tasks. However, pure geometric information is insufficient for many field applications that require appearance…

Accurate detection of obstacles in 3D is an essential task for autonomous driving and intelligent transportation. In this work, we propose a general multimodal fusion framework FusionPainting to fuse the 2D RGB image and 3D point clouds at…

We are interested in reconstructing the mesh representation of object surfaces from point clouds. Surface reconstruction is a prerequisite for downstream applications such as rendering, collision avoidance for planning, animation, etc.…

Representing the semantics of words is a long-standing problem for the natural language processing community. Most methods compute word semantics given their textual context in large corpora. More recently, researchers attempted to…

Under any Multiclass Classification (MCC) setting defined by a collection of labeled point-cloud specified by a feature-set, we extract only stochastic partial orderings from all possible triplets of point-cloud without explicitly measuring…

Text-based person search aims to retrieve images of a certain pedestrian by a textual description. The key challenge of this task is to eliminate the inter-modality gap and achieve the feature alignment across modalities. In this paper, we…

In this paper, we introduce the HexPlane representation for 3D semantic scene understanding. Specifically, we first design the View Projection Module (VPM) to project the 3D point cloud into six planes to maximally retain the original…