发表机构
Sungkyunkwan University; Electronics and Telecommunications Research Institute; Yonsei University（成均馆大学; 电子通信研究院; 延世大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对4D高斯溅射中运动表达与存储效率的权衡，提出自适应容量锚定高斯溅射框架，通过调整锚点的神经高斯数量和特征通道实现紧凑动态辐射场，在多数据集上显著压缩存储且不降低质量。
AI 中文摘要
近期4D高斯溅射（4DGS）的进展实现了高保真、实时的时空渲染，但暴露出运动表达性与存储效率之间的根本权衡。基于锚点的设计虽通过锚点级参数共享实现了紧凑性，但其刚性的均匀参数化方式为每个锚点设定了固定的神经高斯数量和特征预算。因此，保真度不足的问题通过过度增加锚点密度而非针对性地轻量提升神经高斯数量或特征容量来解决，导致内存浪费。为克服这种刚性，我们提出一种自适应容量的基于锚点的框架，可根据局部时空需求动态分配表示容量。自适应锚点基数会改变每个锚点的神经高斯数量，将图元集中在几何或运动复杂区域，同时抑制冗余；并行的自适应锚点特征掩码则会调节锚点级特征通道，为复杂区域分配丰富特征，为简单区域分配轻量表示。在MPEG、Panoptic Sports和N3DV数据集上的实验表明，我们的方法在不降低视觉质量的情况下实现了显著的存储减少，尤其在具有复杂运动的挑战性MPEG序列上，其压缩率比最先进的基于锚点的方法高出1.5倍，同时保持了相当的质量。
英文摘要
Recent advances in 4D Gaussian Splatting (4DGS) enable high-fidelity, real-time spatiotemporal rendering, but expose a fundamental trade-off between motion expressiveness and storage efficiency. While anchor-based designs achieve compactness through anchor-level parameter sharing, their rigid uniform parametrization enforces fixed Neural Gaussian counts and feature budgets per anchor. Consequently, insufficient fidelity is addressed by excessive anchor density, rather than lightweight, targeted increases in Neural Gaussian count or feature capacity, resulting in memory waste. To overcome this rigidity, we introduce an adaptive-capacity anchor-based framework that dynamically allocates the representational capacity based on local spatiotemporal demands. Adaptive Anchor Cardinality varies the number of Neural Gaussians per anchor, concentrating primitives in regions of high geometric or motion complexity while suppressing redundancy. In parallel, Adaptive Anchor Feature Masking modulates anchor-level feature channels, assigning rich features to complex regions and lightweight representations to simpler ones. Experiments on MPEG, Panoptic Sports, and N3DV datasets demonstrate substantial storage reduction without degrading visual quality. Notably, on challenging MPEG sequences with complex motion, our method achieves up to 1.5x higher compression than state-of-the-art anchor-based methods while preserving comparable quality.
Comments9 pages, 8 figures. Accepted to ACM Multimedia 2026
