Abstract
We present a 4D Gaussian Splatting framework for the Sparse-View Track of the SIGGRAPH Asia 2026 Volumetric Video Challenge, which requires dynamic scene reconstruction from only six cameras with wide baselines. To achieve robust dynamic reconstruction under such sparse views, our framework integrates three components. (1) Region-adaptive spatial priors: We use foreground masks to guide Gaussian initialization and mask voting to control densification separately for the dynamic foreground and static background. Background geometry is regularized using monocular depth aligned to metric scale. (2) Motion-consistent temporal priors: We provide supervision at intermediate times through frame interpolation and constrain projected Gaussian motion with estimated optical flow. (3) Generative assistance: We place virtual cameras in the widest angular gaps and restore their rendered images using a diffusion-based model conditioned on camera poses. The restored images are iteratively incorporated into training as pseudo-supervision. On the validation set, our framework improves full-frame PSNR from 25.60 dB for the baseline to 29.75 dB. On the official test benchmark, it achieves 30.04 dB full-frame PSNR and 27.88 dB foreground PSNR, ranking first overall in the Sparse-View Track.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Wang, S., Yang, Z., Tian, K., Liu, Y., Liu, B., Du, H., Huang, T., Wu, J., & Yu, T. (2026). Sparse-View 4D Gaussian Splatting via Spatiotemporal Priors and Generative Assistance. https://omanscience.com/en/articles/sparse-view-4d-gaussian-splatting-via-spatiotemporal-priors-and-generative-assistance
MLA 9
Wang, Shengqi, et al. "Sparse-View 4D Gaussian Splatting via Spatiotemporal Priors and Generative Assistance." https://omanscience.com/en/articles/sparse-view-4d-gaussian-splatting-via-spatiotemporal-priors-and-generative-assistance.
Chicago (author–date)
Wang, Shengqi, Zhengxian Yang, Kaiwen Tian, Yang Liu, Bowen Liu, Hua Du, Taicheng Huang, Jiamin Wu, and Tao Yu. 2026. "Sparse-View 4D Gaussian Splatting via Spatiotemporal Priors and Generative Assistance." https://omanscience.com/en/articles/sparse-view-4d-gaussian-splatting-via-spatiotemporal-priors-and-generative-assistance.
Harvard
Wang, S., Yang, Z., Tian, K., Liu, Y., Liu, B., Du, H., Huang, T., Wu, J. and Yu, T. (2026) 'Sparse-View 4D Gaussian Splatting via Spatiotemporal Priors and Generative Assistance', Available at: https://omanscience.com/en/articles/sparse-view-4d-gaussian-splatting-via-spatiotemporal-priors-and-generative-assistance.
Vancouver
Wang S, Yang Z, Tian K, Liu Y, Liu B, Du H, et al. Sparse-View 4D Gaussian Splatting via Spatiotemporal Priors and Generative Assistance. https://omanscience.com/en/articles/sparse-view-4d-gaussian-splatting-via-spatiotemporal-priors-and-generative-assistance
IEEE
S. Wang, Z. Yang, K. Tian, Y. Liu, B. Liu, H. Du, T. Huang, J. Wu, and T. Yu, "Sparse-View 4D Gaussian Splatting via Spatiotemporal Priors and Generative Assistance," https://omanscience.com/en/articles/sparse-view-4d-gaussian-splatting-via-spatiotemporal-priors-and-generative-assistance.