Dynamic Gaussian Scene Reconstruction from Unsynchronized Videos
This work addresses a practical issue in computer vision for applications like film production and virtual reality, but it is incremental as it builds upon existing 4DGS methods by adding a temporal alignment module.
The paper tackles the problem of dynamic scene reconstruction from unsynchronized multi-view videos, which often suffer from temporal misalignment, by proposing a coarse-to-fine temporal alignment strategy integrated into 4D Gaussian Splatting frameworks, resulting in significantly enhanced reconstruction quality over baseline methods.
Multi-view video reconstruction plays a vital role in computer vision, enabling applications in film production, virtual reality, and motion analysis. While recent advances such as 4D Gaussian Splatting (4DGS) have demonstrated impressive capabilities in dynamic scene reconstruction, they typically rely on the assumption that input video streams are temporally synchronized. However, in real-world scenarios, this assumption often fails due to factors like camera trigger delays or independent recording setups, leading to temporal misalignment across views and reduced reconstruction quality. To address this challenge, a novel temporal alignment strategy is proposed for high-quality 4DGS reconstruction from unsynchronized multi-view videos. Our method features a coarse-to-fine alignment module that estimates and compensates for each camera's time shift. The method first determines a coarse, frame-level offset and then refines it to achieve sub-frame accuracy. This strategy can be integrated as a readily integrable module into existing 4DGS frameworks, enhancing their robustness when handling asynchronous data. Experiments show that our approach effectively processes temporally misaligned videos and significantly enhances baseline methods.