SharpTimeGS:

Sharp and Stable Dynamic Gaussian Splatting via Lifespan Modulation

Zhanfeng Liao, Jiajun Zhang, Hanzhang Tu, Zhixi Wang, Yunqi Gao, Hongwen Zhang, Yebin Liu

ArXiv

Abstract

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.


Method

Fig 1. The pipeline of SharpTimeGS. We represent a dynamic scene using Gaussian primitives whose temporal visibility adapts to the actual lifespan of each point. To achieve this, we introduce a lifespan-dependent parameter r that modulates the temporal Gaussian, allowing a single primitive to accurately model its full lifespan. Moreover, through the modulation terms, the static part can be completely static and still able to express dynamic parts (the static and fast dynamic regions will be transformed into equations of motion in red and blue boxes, respectively). Note that the formulas in the boxes are only approximations. During optimization, all Gaussian representations remain identical.

 

Fig 2. Results in open-source dataset.

 

Fig 3. Results in our dataset.

 

 

Fig 4. More results in our dataset.

 

 

Fig 5. Results in our viewer.

 

 

Fig 6. Results in iPad.

 

Citation

              @article{liao2026sharptimegs,
                      title={SharpTimeGS: Sharp and Stable Dynamic Gaussian Splatting via Lifespan Modulation},
                      author={Liao, Zhanfeng and Zhang, Jiajun and Tu, Hanzhang and Wang, Zhixi and Gao, Yunqi and Zhang, Hongwen and Liu, Yebin},
                      journal={arXiv e-prints},
                      year={2026}
                    }