用于可部署连续时间4D高斯重建的摊销锚点细化
Amortized Anchor Refinement for Deployable Continuous-Time 4D Gaussian Reconstruction
浏览论文内容
中文总结 AI 辅助
针对独立XR头显上连续时间4D重建的部署难题，提出Amortized Anchor Refinement方法，结合冻结骨干网络、短期优化及拓扑约束，在Stage-Capture基准取得24.31±2.22dB，可在消费级GPU完成重建并在XR头显回放。
中文摘要 AI 辅助
连续时间4D重建在独立XR头显上仍不实用，逐场景优化需要部署不可行的计算资源，而较低预算会导致性能崩溃而非逐渐下降；前馈预测速度快，但难以恢复场景特定细节。我们提出Amortized Anchor Refinement，它使用冻结的骨干网络预测初始高斯表示，并在固定计算预算下进行短期优化以使其适配场景，同时设置容量下限以保持表示密度。随后的无训练阶段应用持续同伦约束来修剪不稳定的高斯，同时保留拓扑持续结构，并将得到的轨迹直接作为场景流输出。在Stage-Capture基准上，Amortized Anchor Refinement取得了24.31±2.22dB的成绩，部署实验表明其可在单个消费级GPU上以目标预算内完成重建，并在独立XR头显上实现回放。
英文摘要
Continuous-time 4D reconstruction remains impractical on standalone XR headsets. Per-scene optimization demands deployment-infeasible compute, and lower budgets cause collapse rather than degrade gradually. Feed-forward prediction is fast, but struggle to recover scene-specific detail. We present Amortized Anchor Refinement, which uses a frozen backbone to predict an initial Gaussian representation and a short optimization to specialize it under a fixed compute budget, with a capacity floor preserving representational density. A training-free stage then applies a persistent-homology constraint to prune unstable Gaussians while preserving topologically persistent structures, and streams the resulting trajectories directly as scene flow. On the Stage-Capture benchmark, Amortized Anchor Refinement achieves 24.31$\pm$2.22dB, while our deployment experiments demonstrate reconstruction within the target budget on a single consumer GPU and playback on a standalone XR headset.
发表机构
- South Dakota State University（南达科他州立大学）
- KTH Royal Institute of Technology（瑞典皇家理工学院）
- Aalto University（阿尔托大学）
机构由 AI 辅助整理，请以论文原文为准。
