D-FCGS：动态高斯点云的前馈压缩用于自由视角视频
D-FCGS: Feedforward Compression of Dynamic Gaussian Splatting for Free-Viewpoint Videos
AI总结：
D-FCGS提出了一种动态高斯点云的前馈压缩方法，通过标准化帧组结构、双先验熵模型和控制点引导机制，实现高效压缩与高质量视图一致性。
摘要：
自由视角视频（FVV）能够提供沉浸式的3D体验，但动态3D表示的有效压缩仍然是一个重大挑战。现有的动态3D高斯点云方法将重建与依赖优化的压缩和定制化的运动格式耦合在一起，限制了通用性和标准化。为此，我们提出了D-FCGS，一种新的动态高斯点云前馈压缩框架。关键创新包括：（1）一种标准化的帧组（GoF）结构，具有I-P编码，利用稀疏控制点提取帧间运动张量；（2）一种双先验意识熵模型，融合超先验和时空先验以实现准确的率估计；（3）一种由控制点引导的运动补偿机制和细化网络，以增强视图一致的保真度。在从多视角视频中提取的高斯帧上训练，D-FCGS能够跨多样场景以零样本方式泛化。实验表明，其在率失真性能上与基于优化的方法相当，相比基线实现了超过17倍的压缩，同时在不同视角下保持视觉质量。这项工作推进了动态3DGS的前馈压缩，为可扩展的FVV传输和存储提供了支持，以满足沉浸式应用的需求。
英文摘要：
Free-Viewpoint Video (FVV) enables immersive 3D experiences, but efficient compression of dynamic 3D representation remains a major challenge. Existing dynamic 3D Gaussian Splatting methods couple reconstruction with optimization-dependent compression and customized motion formats, limiting generalization and standardization. To address this, we propose D-FCGS, a novel Feedforward Compression framework for Dynamic Gaussian Splatting. Key innovations include: (1) a standardized Group-of-Frames (GoF) structure with I-P coding, leveraging sparse control points to extract inter-frame motion tensors; (2) a dual prior-aware entropy model that fuses hyperprior and spatial-temporal priors for accurate rate estimation; (3) a control-point-guided motion compensation mechanism and refinement network to enhance view-consistent fidelity. Trained on Gaussian frames derived from multi-view videos, D-FCGS generalizes across diverse scenes in a zero-shot fashion. Experiments show that it matches the rate-distortion performance of optimization-based methods, achieving over 17 times compression compared to the baseline while preserving visual quality across viewpoints. This work advances feedforward compression of dynamic 3DGS, facilitating scalable FVV transmission and storage for immersive applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
