Related papers: DSM: Constructing a Diverse Semantic Map for 3D Vi…
The Structure from Motion (SfM) challenge in computer vision is the process of recovering the 3D structure of a scene from a series of projective measurements that are calculated from a collection of 2D images, taken from different…
We propose SemGauss-SLAM, a dense semantic SLAM system utilizing 3D Gaussian representation, that enables accurate 3D semantic mapping, robust camera tracking, and high-quality rendering simultaneously. In this system, we incorporate…
Scene text image contains two levels of contents: visual texture and semantic information. Although the previous scene text recognition methods have made great progress over the past few years, the research on mining semantic information to…
The evolution of 3D visual content calls for innovative methods for modelling shapes based on their intended usage, function and role in a complex scenario. Even if different attempts have been done in this direction, shape modelling still…
In recent years, the paradigm of neural implicit representations has gained substantial attention in the field of Simultaneous Localization and Mapping (SLAM). However, a notable gap exists in the existing approaches when it comes to scene…
With the emergence of LLMs and their integration with other data modalities, multi-modal 3D perception attracts more attention due to its connectivity to the physical world and makes rapid progress. However, limited by existing datasets,…
Visual scene understanding is an important capability that enables robots to purposefully act in their environment. In this paper, we propose a novel approach to object-class segmentation from multiple RGB-D views using deep learning. We…
With the popularity of monocular videos generated by video sharing and live broadcasting applications, reconstructing and editing dynamic scenes in stationary monocular cameras has become a special but anticipated technology. In contrast to…
Modeling and understanding the 3D world is crucial for various applications, from augmented reality to robotic navigation. Recent advancements based on 3D Gaussian Splatting have integrated semantic information from multi-view images into…
For mobile robots to operate autonomously in general environments, perception is required in the form of a dense metric map. For this purpose, we present the stochastic triangular mesh (STM) mapping technique: a 2.5-D representation of the…
Classification of different object surface material types can play a significant role in the decision-making algorithms for mobile robots and autonomous vehicles. RGB-based scene-level semantic segmentation has been well-addressed in the…
3D visual grounding (3DVG) is a critical task in scene understanding that aims to identify objects in 3D scenes based on text descriptions. However, existing methods rely on separately pre-trained vision and text encoders, resulting in a…
Recent advancements in 3D Gaussian Splatting(3DGS) have significantly improved semantic scene understanding, enabling natural language queries to localize objects within a scene. However, existing methods primarily focus on embedding…
As the foundation of driverless vehicle and intelligent robots, Simultaneous Localization and Mapping(SLAM) has attracted much attention these days. However, non-geometric modules of traditional SLAM algorithms are limited by data…
Camera-based 3D semantic scene completion (SSC) provides dense geometric and semantic perception for autonomous driving and robotic navigation. However, existing methods rely on a coupled encoder to deliver both semantic and geometric…
Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image. Most existing methods use independent image-text encoding and apply complex hand-crafted modules or…
The availability of real-time semantics greatly improves the core geometric functionality of SLAM systems, enabling numerous robotic and AR/VR applications. We present a new methodology for real-time semantic mapping from RGB-D sequences…
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…
Multimodal fusion of remote sensing images serves as a core technology for overcoming the limitations of single-source data and improving the accuracy of surface information extraction, which exhibits significant application value in fields…
Prompt-driven scene synthesis allows users to generate complete 3D environments from textual descriptions. Current text-to-scene methods often struggle with complex geometries and object transformations, and tend to show weak adherence to…