发表机构
The University of Hong Kong; University of Newcastle; Santa Clara University; Futurewei Technologies, Inc.（香港大学; 纽卡斯尔大学; 圣克拉拉大学; 华为主导未来技术公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出面向3D/4D高斯溅射的可控合成基准M$^3$ISR，含25个场景等，设5个赛道，评估发现静态重建质量差异小但存储成本差异大，为相关研究提供测试平台。
AI 中文摘要
高保真自由视点视频（FVV）与交互式渲染日益依赖显式高斯表示，但其实际部署仍受限于表示规模、动态更新及计算成本。现有多视图视频基准测试提供了宝贵的真实采集内容，但难以分离可控相机几何、表示效率与时间冗余的影响。我们引入M$^3$ISR，这是一个针对3D和4D高斯溅射（3DGS/4DGS）的可控合成基准测试。该基准测试包含5组室内外场景的25个场景、2种相机/运动配置、6个同步1080p视角，以及密集的真值标注，涵盖RGB、相机参数、深度、语义与实例分割、静态-动态掩码。共心相机设计有意分离了角度视角变化，支持对新视角合成与表示效率的可控评估。我们将M$^3$ISR划分为5个互补赛道，覆盖3DGS合成、4DGS合成、4DGS流式传输、3DGS压缩、4DGS压缩。代表性基线结果显示，静态重建质量差异较小，但表示存储差异显著；评估的流式传输方法报告的训练或重建成本远高于对应的离线动态重建基线。我们进一步定义了3DGS与4DGS的前馈压缩任务，并提供参考率-失真公式与初步基线评估。该基准测试旨在成为可控且互补的测试平台，用于系统研究基于高斯的FVV重建、压缩与流式传输。
英文摘要
High-fidelity free-viewpoint video (FVV) and interactive rendering increasingly rely on explicit Gaussian representations, yet practical deployment remains constrained by representation size, dynamic updates, and computational cost. Existing multi-view video benchmarks provide valuable real-captured content, but they make it difficult to isolate the effects of controlled camera geometry, representation efficiency, and temporal redundancy. We introduce M$^3$ISR, a controlled synthetic benchmark for 3D and 4D Gaussian Splatting (3DGS/4DGS). The benchmark contains 25 scenes from five indoor and outdoor scene groups, two camera/motion configurations, six synchronized 1080p views, and dense ground-truth annotations including RGB, camera parameters, depth, semantic and instance segmentation, and static--dynamic masks. The shared-center camera design intentionally isolates angular view variation and enables controlled evaluation of novel-view synthesis and representation efficiency. We organize M$^3$ISR into five complementary tracks covering 3DGS synthesis, 4DGS synthesis, 4DGS streaming, 3DGS compression, and 4DGS compression. Representative baseline results show small differences in static reconstruction quality but substantial differences in representation storage, while the evaluated streaming methods exhibit substantially higher reported training or reconstruction cost than the corresponding offline dynamic reconstruction baselines. We further define feedforward compression tasks for 3DGS and 4DGS and provide reference rate--distortion formulations and preliminary baseline evaluations. The benchmark is intended as a controlled and complementary testbed for systematic study of Gaussian-based FVV reconstruction, compression, and streaming.
