Related papers: SPHERE: Semantic-PHysical Engaged REpresentation f…

Recently, 3D Gaussian Splatting (3D-GS) has achieved significant success in real-time, high-quality 3D scene rendering. However, it faces several challenges, including Gaussian redundancy, limited ability to capture view-dependent effects,…

Real-time 3D reconstruction of surgical scenes plays a vital role in computer-assisted surgery, holding a promise to enhance surgeons' visibility. Recent advancements in 3D Gaussian Splatting (3DGS) have shown great potential for real-time…

Real-time scene parsing is a fundamental feature for autonomous driving vehicles with multiple cameras. In this letter we demonstrate that sharing semantics between cameras with different perspectives and overlapped views can boost the…

Robotics applications often rely on scene reconstructions to enable downstream tasks. In this work, we tackle the challenge of actively building an accurate map of an unknown scene using an RGB-D camera on a mobile platform. We propose a…

Semantic scene segmentation plays a critical role in a wide range of robotics applications, e.g., autonomous navigation. These applications are accompanied by specific computational restrictions, e.g., operation on low-power GPUs, at…

Semantic Scene Completion (SSC) refers to the task of inferring the 3D semantic segmentation of a scene while simultaneously completing the 3D shapes. We propose PALNet, a novel hybrid network for SSC based on single depth. PALNet utilizes…

Simultaneous Localization and Mapping (SLAM) is a critical task in robotics, enabling systems to autonomously navigate and understand complex environments. Current SLAM approaches predominantly rely on geometric cues for mapping and…

This position paper argues for the use of \emph{structured generative models} (SGMs) for the understanding of static scenes. This requires the reconstruction of a 3D scene from an input image (or a set of multi-view images), whereby the…

Current Visual Simultaneous Localization and Mapping (VSLAM) systems often struggle to create maps that are both semantically rich and easily interpretable. While incorporating semantic scene knowledge aids in building richer maps with…

3D scene graphs have recently emerged as a powerful high-level representation of 3D environments. A 3D scene graph describes the environment as a layered graph where nodes represent spatial concepts at multiple levels of abstraction and…

Vehicle detection and localization in complex traffic scenarios pose significant challenges due to the interference of moving objects. Traditional methods often rely on outlier exclusions or semantic segmentations, which suffer from low…

Modern scene reconstruction methods, such as 3D Gaussian Splatting, deliver photo-realistic novel view synthesis at real-time speeds, yet their adoption in interactive graphics applications has been limited. A major bottleneck is the…

Recent advances in Gaussian Splatting based 3D scene representation have shown two major trends: semantics-oriented approaches that focus on high-level understanding but lack explicit 3D geometry modeling, and structure-oriented approaches…

In this paper, we provide a comprehensive overview of existing scene representation methods for robotics, covering traditional representations such as point clouds, voxels, signed distance functions (SDF), and scene graphs, as well as more…

This paper introduces VisHall3D, a novel two-stage framework for monocular semantic scene completion that aims to address the issues of feature entanglement and geometric inconsistency prevalent in existing methods. VisHall3D decomposes the…

Following the advent of NeRFs, 3D Gaussian Splatting (3D-GS) has paved the way to real-time neural rendering overcoming the computational burden of volumetric methods. Following the pioneering work of 3D-GS, several methods have attempted…

Semantic Scene Completion (SSC) has emerged as a pivotal approach for jointly learning scene geometry and semantics, enabling downstream applications such as navigation in mobile robotics. The recent generalization to Panoptic Scene…

Semantic scene completion is the task of predicting a complete 3D representation of volumetric occupancy with corresponding semantic labels for a scene from a single point of view. Previous works on Semantic Scene Completion from RGB-D data…

In the realm of autonomous driving, achieving precise 3D reconstruction of the driving environment is critical for ensuring safety and effective navigation. Neural Radiance Fields (NeRF) have shown promise in creating highly detailed and…

Open-vocabulary scene understanding is crucial for robotic applications, enabling robots to comprehend complex 3D environmental contexts and supporting various downstream tasks such as navigation and manipulation. However, existing methods…