Metraipolis › archive › dc_c33b07770f97
4DGS-Fixer: Generative Sparse-View 4D Gaussian Splatting with Iterative Refinement Guided by Video Diffusion Priors — arXiv:2609.21176
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.21176
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T02:22:59.414Z
- SHA-256 of the archived text
3bd3825e294e7bd92722ab2529f9f031aa6c2d12f3fdb66a31e453ec0c4eb954- Stable URL of this page
https://metraipolis.com/documento/dc_c33b07770f97
How to cite
4DGS-Fixer: Generative Sparse-View 4D Gaussian Splatting with Iterative Refinement Guided by Video Diffusion Priors — arXiv:2609.21176 — arXiv (en), https://arxiv.org/abs/2609.21176 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c33b07770f97 (Metraipolis archive dc_c33b07770f97, sha256 3bd3825e294e7bd92722ab2529f9f031aa6c2d12f3fdb66a31e453ec0c4eb954)
BibTeX
@misc{dcc33b07770f97,
title = {4DGS-Fixer: Generative Sparse-View 4D Gaussian Splatting with Iterative Refinement Guided by Video Diffusion Priors — arXiv:2609.21176},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.21176},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c33b07770f97; sha256 3bd3825e294e7bd92722ab2529f9f031aa6c2d12f3fdb66a31e453ec0c4eb954},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21176. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper addresses the challenges of dynamic scene synthesis from sparse-view videos. Existing methods employ geometric priors, adaptive optimization, or density-control strategies to improve 4D Gaussian modeling under sparse observations. However, they cannot fundamentally resolve the ill-posed problem caused by insufficient observations and missing scene information. Moreover, sparse-view 4D Gaussian Splatting (4DGS) often suffers from poor geometric initialization: with only a few input views, COLMAP typically reconstructs sparse and incomplete point clouds, leaving large scene regions without sufficient Gaussian support and making them difficult to recover through subsequent optimization. To address these limitations, we propose a novel iterative refinement framework based on a video diffusion model to improve the completeness and consistency of dynamic 4D scenes. Specifically, we first estimate multi-view depth maps and fuse them into dense point clouds to provide more complete geometric initialization for a dynamic 4DGS representation. We then employ a pretrained video restoration model to refine sequences rendered along novel camera trajectories at different time steps. The restored sequences serve as pseudo-supervision to regularize and iteratively refine the 4DGS representation. Experiments on a widely used benchmark dataset demonstrate that our method substantially outperforms existing baselines, achieving nearly a 2 dB PSNR improvement over the previous best-performing method. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.21176 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T02:07:36.008Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).