paper-with-me

Papers

CrowdSplat: Exploring Gaussian Splatting For Crowd Rendering

2025-01-29 · Xiaohan Sun, Yinghan Xu, John Dingliana, Carol O'Sullivan

We present CrowdSplat, a novel approach that leverages 3D Gaussian Splatting for real-time, high-quality crowd rendering. Our method utilizes 3D Gaussian functions to represent animated human characters in diverse poses and outfits, which are extracted from monocular videos. We integrate Level of Detail (LoD) rendering to optimize computational efficiency and quality. The CrowdSplat framework consists of two stages: (1) avatar reconstruction and (2) crowd synthesis. The framework is also optimized for GPU memory usage to enhance scalability. Quantitative and qualitative evaluations show that CrowdSplat achieves good levels of rendering quality, memory efficiency, and computational performance. Through these experiments, we demonstrate that CrowdSplat is a viable solution for dynamic, realistic crowd simulation in real-time applications.

📄 PDF Abstract BibTeX arXiv:2501.17792

Code (1)

RockyXu66/GaussianSplattingViewer 공식 구현 pytorch

Tasks

Computational EfficiencyGPU

Similar Papers 제목 키워드 기반

Evaluating CrowdSplat: Perceived Level of Detail for Gaussian Crowds

2025-01-28 · Xiaohan Sun, Yinghan Xu, John Dingliana, Carol O'Sullivan

Efficient and realistic crowd rendering is an important element of many real-time graphics applications such as Virtual Reality (VR) and games. To this end, Levels of Detail (LOD) avatar representations such as polygonal…

From Volume Rendering to 3D Gaussian Splatting: Theory and Applications

2025-10-20 · Vitor Pereira Matias, Daniel Perazzo, Vinicius Silva, Alberto Raposo 외 arxiv

The problem of 3D reconstruction from posed images is undergoing a fundamental transformation, driven by continuous advances in 3D Gaussian Splatting (3DGS). By modeling scenes explicitly as collections of 3D Gaussians, …

Novel View Synthesis3D Reconstruction

HybridSplat: Fast Reflection-baked Gaussian Tracing using Hybrid Splatting

2025-12-09 · Chang Liu, Hongliang Yuan, Lianghao Zhang, Sichao Wang 외 arxiv

Rendering complex reflection of real-world scenes using 3D Gaussian splatting has been a quite promising solution for photorealistic novel view synthesis, but still faces bottlenecks especially in rendering speed and mem…

Novel View Synthesis

Recent Advances in 3D Gaussian Splatting

2024-03-17 · Tong Wu, Yu-Jie Yuan, Ling-Xiao Zhang, Jie Yang 외

The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis. Unlike neural implicit representations like Neural Radiance Fields (NeRF) that represent a 3D scene with …

3DGS3D ReconstructionDynamic ReconstructionNeRF+1

Pushing Rendering Boundaries: Hard Gaussian Splatting

2024-12-06 · Qingshan Xu, Jiequan Cui, Xuanyu Yi, Yuxuan Wang 외

3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner. During training, it relies heavily on the average magnitude of view-space positional gradients …

3DGSNovel View Synthesis