发表机构
Hanyang University; Hanyang University ERICA（汉阳大学; 汉阳大学衣理校区）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对快速运动大帧间位移下4DGS方法失效问题，提出SPIN-4DGS，从显式时空位置学习高斯属性，用轻量级网络预测属性，避免高内存开销，实验证明该方法在大位移下保真度更高，提升了PSNR和SSIM。
AI 中文摘要
近期的4D高斯点云渲染（4DGS）方法在大帧间位移的快速运动下常失效，训练时高斯属性学习不佳，重建中快速移动对象易丢失。本文引入时空位置隐式网络SPIN-4DGS，从显式收集的时空位置学习高斯属性而非建模时间位移，在大帧间位移快速运动下实现更精确的点云渲染。通过基于光栅化重建损失训练的轻量级前馈网络预测属性，避免了跨所有时空位置显式优化属性的高内存开销。实验表明，SPIN-4DGS在大位移下保真度更高，在CMU全景数据集中具有挑战性的运动场景上，PSNR和SSIM有明显提升。
英文摘要
Recent 4D Gaussian Splatting (4DGS) methods often fail under fast motion with large inter-frame displacements, where Gaussian attributes are poorly learned during training, and fast-moving objects are often lost from the reconstruction. In this work, we introduce Spatiotemporal Position Implicit Network for 4DGS, coined SPIN-4DGS, which learns Gaussian attributes from explicitly collected spatiotemporal positions rather than modeling temporal displacements, thereby enabling more faithful splatting under fast motions with large inter-frame displacements. To avoid the heavy memory overhead of explicitly optimizing attributes across all spatiotemporal positions, we instead predict them with a lightweight feed-forward network trained under a rasterization-based reconstruction loss. Consequently, SPIN-4DGS learns shared representations across Gaussians, effectively capturing spatiotemporal consistency and enabling stable high-quality Gaussian splatting even under challenging motions. Across extensive experiments, SPIN-4DGS consistently achieves higher fidelity under large displacements, with clear improvements in PSNR and SSIM on challenging sports scenes from the CMU Panoptic dataset. For example, SPIN-4DGS notably outperforms the strongest baseline, D3DGS, by achieving +1.83 higher PSNR on the Basketball scene.
CommentsAccepted at ICLR 2026. Project page at https://seung-gyeom.github.io/SPIN-4DGS
