paper-with-me

홈 › Papers

Toy-GS: Assembling Local Gaussians for Precisely Rendering Large-Scale Free Camera Trajectories

2024-12-13 · Xiaohan Zhang, Zhenyu Sun, Yukui Qiu, Junyan Su, Qi Liu

Currently, 3D rendering for large-scale free camera trajectories, namely, arbitrary input camera trajectories, poses significant challenges: 1) The distribution and observation angles of the cameras are irregular, and various types of scenes are included in the free trajectories; 2) Processing the entire point cloud and all images at once for large-scale scenes requires a substantial amount of GPU memory. This paper presents a Toy-GS method for accurately rendering large-scale free camera trajectories. Specifically, we propose an adaptive spatial division approach for free trajectories to divide cameras and the sparse point cloud of the entire scene into various regions according to camera poses. Training each local Gaussian in parallel for each area enables us to concentrate on texture details and minimize GPU memory usage. Next, we use the multi-view constraint and position-aware point adaptive control (PPAC) to improve the rendering quality of texture details. In addition, our regional fusion approach combines local and global Gaussians to enhance rendering quality with an increasing number of divided areas. Extensive experiments have been carried out to confirm the effectiveness and efficiency of Toy-GS, leading to state-of-the-art results on two public large-scale datasets as well as our SCUTic dataset. Our proposal demonstrates an enhancement of 1.19 dB in PSNR and conserves 7 G of GPU memory when compared to various benchmarks.

📄 PDF Abstract BibTeX arXiv:2412.10078

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

Similar Papers 제목 키워드 기반

Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives

2024-11-30 · CVPR 2025 1 · Alex Hanson, Allen Tu, Geng Lin, Vasu Singla 외

3D Gaussian Splatting (3D-GS) is a recent 3D scene reconstruction technique that enables real-time rendering of novel views by modeling scenes as parametric point clouds of differentiable 3D Gaussians. However, its rende…

3D Scene ReconstructionNeRF

VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians

2025-06-03 · Pengchong Hu, Zhizhong Han

Jointly estimating camera poses and mapping scenes from RGBD images is a fundamental task in simultaneous localization and mapping (SLAM). State-of-the-art methods employ 3D Gaussians to represent a scene, and render the…

GPUSimultaneous Localization and Mapping

DynaSurfGS: Dynamic Surface Reconstruction with Planar-based Gaussian Splatting

2024-08-26 · Weiwei Cai, Weicai Ye, Peng Ye, Tong He 외

Dynamic scene reconstruction has garnered significant attention in recent years due to its capabilities in high-quality and real-time rendering. Among various methodologies, constructing a 4D spatial-temporal representat…

Surface Reconstruction

SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction

2026-04-03 · Zicheng Zhang, Xiangting Meng, Ke Wu, Wenchao Ding arxiv

Recent progress in feed-forward 3D Gaussian Splatting (3DGS) has notably improved rendering quality. However, the spatially uniform and highly redundant 3DGS map generated by previous feed-forward 3DGS methods limits the…

Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering

2023-11-30 · CVPR 2024 1 · Tao Lu, Mulin Yu, Linning Xu, Yuanbo Xiangli 외

Neural rendering methods have significantly advanced photo-realistic 3D scene rendering in various academic and industrial applications. The recent 3D Gaussian Splatting method has achieved the state-of-the-art rendering…

Neural Rendering