SharpTimeGS：通过生命周期调制实现清晰稳定的动态高斯泼溅
SharpTimeGS: Sharp and Stable Dynamic Gaussian Splatting via Lifespan Modulation
提出可学习的生命周期参数，将高斯的时序可见性从高斯衰减改为平顶分布，并据此调制运动幅度与致密化策略，为动态高斯泼溅中静态与动态区域的解耦优化提供了可复用的技术手段。
原文依据 we introduce a learnable lifespan parameter that reformulates temporal visibility from a Gaussian-shaped decay into a flat-top profile
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论动态场景的新视角合成是实现逼真 4D 重建与沉浸式视觉体验的基础。基于高斯表示的最新进展显著提升了实时渲染质量，然而现有方法在表示与优化中仍难以平衡长期静态区域与短期动态区域。为此，我们提出 SharpTimeGS，一种生命周期感知的 4D 高斯框架，在统一表示下实现对静态与动态区域的时序自适应建模。具体而言，我们引入可学习的生命周期参数，将时序可见性从高斯形衰减重构为平顶分布，使基元在其预期持续时间内保持持续活跃，避免冗余致密化。此外，学习到的生命周期调制每个基元的运动，减少长寿命静态点的漂移，同时保留短寿命动态点的无约束运动。这有效解耦了运动幅度与持续时间，在提升长期稳定性的同时不损害动态保真度。进一步，我们设计了生命周期-速度感知的致密化策略，通过向运动显著区域分配更多容量、保持静态区域紧凑稳定，缓解静态与动态区域间的优化不平衡。在多个基准上的大量实验表明，我们的方法在实现最优性能的同时，在单块 RTX 4090 上支持高达 4K 分辨率、100 FPS 的实时渲染。
英文原文摘要 1613 字符
Novel view synthesis of dynamic scenes is fundamental to achieving photorealistic 4D reconstruction and immersive visual experiences. Recent progress in Gaussian-based representations has significantly improved real-time rendering quality, yet existing methods still struggle to maintain a balance between long-term static and short-term dynamic regions in both representation and optimization. To address this, we present SharpTimeGS, a lifespan-aware 4D Gaussian framework that achieves temporally adaptive modeling of both static and dynamic regions under a unified representation. Specifically, we introduce a learnable lifespan parameter that reformulates temporal visibility from a Gaussian-shaped decay into a flat-top profile, allowing primitives to remain consistently active over their intended duration and avoiding redundant densification. In addition, the learned lifespan modulates each primitive's motion, reducing drift in long-lived static points while retaining unrestricted motion for short-lived dynamic ones. This effectively decouples motion magnitude from temporal duration, improving long-term stability without compromising dynamic fidelity. Moreover, we design a lifespan-velocity-aware densification strategy that mitigates optimization imbalance between static and dynamic regions by allocating more capacity to regions with pronounced motion while keeping static areas compact and stable. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art performance while supporting real-time rendering up to 4K resolution at 100 FPS on one RTX 4090.