Related papers: LESV: Language Embedded Sparse Voxel Fusion for Op…

Applying Gaussian Splatting to perception tasks for 3D scene understanding is becoming increasingly popular. Most existing works primarily focus on rendering 2D feature maps from novel viewpoints, which leads to an imprecise 3D language…

Recent breakthroughs in Visual Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have significantly advanced 3D scene perception towards language-driven cognition. However, existing 3D language models struggle with sparse,…

Open-vocabulary panoptic reconstruction is crucial for advanced robotics and simulation. However, existing 3D reconstruction methods, such as NeRF or Gaussian Splatting variants, often struggle to achieve the real-time inference frequency…

3D Gaussian Splatting (3DGS) has emerged as a promising approach for 3D scene representation, offering a reduction in computational overhead compared to Neural Radiance Fields (NeRF). However, 3DGS is susceptible to high-frequency artifacts…

Open-vocabulary semantic mapping enables robots to spatially ground previously unseen concepts without requiring predefined class sets. Current training-free methods commonly rely on multi-view fusion of semantic embeddings into a 3D map,…

Open-vocabulary segmentation enables pixel-level recognition from an open set of textual categories, allowing generalization beyond fixed classes. Despite great potential in remote sensing, progress in this area remains largely limited to…

Open-vocabulary semantic segmentation (OVSS) extends traditional closed-set segmentation by enabling pixel-wise annotation for both seen and unseen categories using arbitrary textual descriptions. While existing methods leverage…

Open-vocabulary 3D visual grounding and reasoning aim to localize objects in a scene based on implicit language descriptions, even when they are occluded. This ability is crucial for tasks such as vision-language navigation and autonomous…

Understanding 3D scenes is pivotal for autonomous driving, robotics, and augmented reality. Recent semantic Gaussian Splatting approaches leverage large-scale 2D vision models to project 2D semantic features onto 3D scenes. However, they…

Modeling open-vocabulary language fields in 3D is essential for intuitive human-AI interaction and querying within physical environments. State-of-the-art approaches, such as LangSplat, leverage 3D Gaussian Splatting to efficiently…

We address the issue of the exploding computational requirements of recent State-of-the-art (SOTA) open set multimodel 3D mapping (dense 3D mapping) algorithms and present Voxel-Aggregated Feature Synthesis (VAFS), a novel approach to dense…

In the perception task of autonomous driving, multi-modal methods have become a trend due to the complementary characteristics of LiDAR point clouds and image data. However, the performance of multi-modal methods is usually limited by the…

Online construction of open-ended language scenes is crucial for robotic applications, where open-vocabulary interactive scene understanding is required. Recently, neural implicit representation has provided a promising direction for online…

We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on adaptive sparse voxels without neural networks or 3D Gaussians. There are two key contributions coupled with the proposed system. The…

Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of text-defined categories, demanding reliable generalization to unseen classes at inference. Although modern vision-language models (VLMs) support…

Open-vocabulary querying in 3D space is challenging but essential for scene understanding tasks such as object localization and segmentation. Language-embedded scene representations have made progress by incorporating language features into…

Recent advances in 3D Gaussian Splatting (3DGS) have enabled Simultaneous Localization and Mapping (SLAM) systems to build photorealistic maps. However, these maps lack the open-vocabulary semantic understanding required for advanced…

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…

Language-guided robotic grasping is a rapidly advancing field where robots are instructed using human language to grasp specific objects. However, existing methods often depend on dense camera views and struggle to quickly update scenes,…

Most previous 3D object detection methods that leverage the multi-modality of LiDAR and cameras utilize the Bird's Eye View (BEV) space for intermediate feature representation. However, this space uses a low x, y-resolution and sacrifices…