鲁棒的、与估计器无关的动态3DGS压缩
Robust, Estimator-Agnostic Dynamic 3DGS Compression
浏览论文内容
中文总结 AI 辅助
提出一种与估计器无关的动态3DGS压缩方法，通过拼接帧组并添加帧索引将时间冗余转为空间冗余，在N3DV数据集上显著提升压缩率，平均BD-rate降低达71.8%。
中文摘要 AI 辅助
动态3D高斯溅射（3DGS）使用每帧独立的高斯集合来建模随时间变化的场景。由于平滑运动，相邻视频帧高度相关，但高斯表示对这种相关性的保留程度因估计器是否随时间跟踪它们而异。一些3DGS压缩方法集成估计以利用时间冗余；在此，我们专注于与估计器无关的鲁棒压缩。我们将帧组拼接成一个高斯集合，为每个高斯添加帧索引，并将其传递给静态（即非时间）3DGS编解码器，从而将时间冗余转换为空间冗余。拼接后的集合在空间上进行分区以限制内存。我们的技术既不需要运动模型，也不需要了解训练方法。在六个N3DV序列上平均，所有六个静态编解码器在跟踪集上相比逐帧编码实现了增益（BD-rate为-42.0%至-71.8%）。在未跟踪集上，除HGSC（似乎与我们的技术不兼容）外，所有编解码器仍与逐帧编码相当（BD-rate为-3.5%至+5.0%）。我们进一步用我们的技术替换D-FCGS的I帧编码，同时保留其P帧编码，得到总体BD-rate为-46.2%。我们提出使用帧间相似性度量来可视化“可跟踪性”。项目可在以下网址获取：https URL。
英文摘要
Dynamic 3D Gaussian splats (3DGS) model time-varying scenes using a separate Gaussian set per frame. While neighboring video frames are highly correlated due to smooth motion, Gaussian representations retain this correlation to varying degrees, depending on whether the estimator tracks them across time. Some 3DGS compression methods integrate the estimation to exploit temporal redundancy; here, we focus on robust compression regardless of the estimator. We concatenate groups of frames into one Gaussian set, augment each Gaussian with a frame index, and pass it to a static (i.e., non-temporal) 3DGS codec, converting temporal redundancy into spatial redundancy. Concatenated sets are spatially partitioned to limit memory. Our technique requires neither a motion model nor knowledge of the training method. Averaged over six N3DV sequences, all six static codecs achieve gains on tracked sets (-42.0% to -71.8% BD-rate) over per-frame coding. On untracked sets, all codecs except HGSC, which appears incompatible with our technique, remain competitive with per-frame coding (-3.5% to +5.0%). We further replace D-FCGS's I-frame coding with our technique while retaining its P-frame coding, yielding an overall BD-rate of -46.2%. We propose to visualize "trackedness" using an inter-frame similarity metric. The project is available at https://wcjj1236.github.io/d3dgs-benchmark.
发表机构
- New York University（纽约大学）
机构由 AI 辅助整理，请以论文原文为准。
