Related papers: LiDAR-RT: Gaussian-based Ray Tracing for Dynamic L…
We present InvRGB+L, a novel inverse rendering model that reconstructs large, relightable, and dynamic scenes from a single RGB+LiDAR sequence. Conventional inverse graphics methods rely primarily on RGB observations and use LiDAR mainly…
Simulation is central to the evaluation of intelligent transportation system (ITS) applications. As ITS increasingly incorporates autonomous vehicle (AV) technologies as fleet vehicles and/or mobile sensors, accurate modeling of their…
Dynamic driving scene reconstruction is of great importance in fields like digital twin system and autonomous driving simulation. However, unacceptable degradation occurs when the view deviates from the input trajectory, leading to…
Efficient neural representations for dynamic video scenes are critical for applications ranging from video compression to interactive simulations. Yet, existing methods often face challenges related to high memory usage, lengthy training…
Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while…
In medical image visualization, path tracing of volumetric medical data like CT scans produces lifelike three-dimensional visualizations. Immersive VR displays can further enhance the understanding of complex anatomies. Going beyond the…
Although dynamic scene reconstruction has long been a fundamental challenge in 3D vision, the recent emergence of 3D Gaussian Splatting (3DGS) offers a promising direction by enabling high-quality, real-time rendering through explicit…
We have recently seen tremendous progress in photo-real human modeling and rendering. Yet, efficiently rendering realistic human performance and integrating it into the rasterization pipeline remains challenging. In this paper, we present…
Real-time global illumination is key to enabling more dynamic and physically realistic worlds in performance-critical applications such as games or any other applications with real-time constraints.Hardware-accelerated ray tracing in modern…
Dense 3D reconstruction has many applications in automated driving including automated annotation validation, multimodal data augmentation, providing ground truth annotations for systems lacking LiDAR, as well as enhancing auto-labeling…
This paper proposes a novel framework for large-scale scene reconstruction based on 3D Gaussian splatting (3DGS) and aims to address the scalability and accuracy challenges faced by existing methods. For tackling the scalability issue, we…
We propose a dense RGBD SLAM system based on 3D Gaussian Splatting that provides metrically accurate pose tracking and visually realistic reconstruction. To this end, we first propose a Gaussian densification strategy based on the rendering…
Explicit neural representations such as 3D Gaussian Splatting (3DGS) enable high-fidelity and real-time novel view synthesis, yet optimize for alpha-composited optical appearance rather than ray-intersectable geometry. In contrast,…
Recent advances in generalizable Gaussian splatting (GS) have enabled feed-forward reconstruction of scenes from tens of input views. Long-LRM notably scales this paradigm to 32 input images at $950\times540$ resolution, achieving 360{\deg}…
3D Gaussian Splatting (3DGS) has recently emerged as a powerful representation of geometry and appearance for dense Simultaneous Localization and Mapping (SLAM). Through rapid, differentiable rasterization of 3D Gaussians, many 3DGS SLAM…
Novel view synthesis has shown rapid progress recently, with methods capable of producing increasingly photorealistic results. 3D Gaussian Splatting has emerged as a promising method, producing high-quality renderings of scenes and enabling…
Modeling scene geometry using implicit neural representation has revealed its advantages in accuracy, flexibility, and low memory usage. Previous approaches have demonstrated impressive results using color or depth images but still have…
We present a method that simultaneously addresses the tasks of dynamic scene novel-view synthesis and six degree-of-freedom (6-DOF) tracking of all dense scene elements. We follow an analysis-by-synthesis framework, inspired by recent work…
Long-term scene changes present challenges to localization systems using a pre-built map. This paper presents a LiDAR-based system that can provide robust localization against those challenges. Our method starts with activation of a mapping…
Simulation systems have become an essential component in the development and validation of autonomous driving technologies. The prevailing state-of-the-art approach for simulation is to use game engines or high-fidelity computer graphics…