Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Yan, Wang, Yixing, Yu, Stella X.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.17932
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915632813965312
author Xu, Yan
Wang, Yixing
Yu, Stella X.
author_facet Xu, Yan
Wang, Yixing
Yu, Stella X.
contents Given just a few glimpses of a scene, can you imagine the movie playing out as the camera glides through it? That's the lens we take on \emph{sparse-input novel view synthesis}, not only as filling spatial gaps between widely spaced views, but also as \emph{completing a natural video} unfolding through space. We recast the task as \emph{test-time natural video completion}, using powerful priors from \emph{pretrained video diffusion models} to hallucinate plausible in-between views. Our \emph{zero-shot, generation-guided} framework produces pseudo views at novel camera poses, modulated by an \emph{uncertainty-aware mechanism} for spatial coherence. These synthesized frames densify supervision for \emph{3D Gaussian Splatting} (3D-GS) for scene reconstruction, especially in under-observed regions. An iterative feedback loop lets 3D geometry and 2D view synthesis inform each other, improving both the scene reconstruction and the generated views. The result is coherent, high-fidelity renderings from sparse inputs \emph{without any scene-specific training or fine-tuning}. On LLFF, DTU, DL3DV, and MipNeRF-360, our method significantly outperforms strong 3D-GS baselines under extreme sparsity.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17932
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion
Xu, Yan
Wang, Yixing
Yu, Stella X.
Computer Vision and Pattern Recognition
Graphics
Given just a few glimpses of a scene, can you imagine the movie playing out as the camera glides through it? That's the lens we take on \emph{sparse-input novel view synthesis}, not only as filling spatial gaps between widely spaced views, but also as \emph{completing a natural video} unfolding through space. We recast the task as \emph{test-time natural video completion}, using powerful priors from \emph{pretrained video diffusion models} to hallucinate plausible in-between views. Our \emph{zero-shot, generation-guided} framework produces pseudo views at novel camera poses, modulated by an \emph{uncertainty-aware mechanism} for spatial coherence. These synthesized frames densify supervision for \emph{3D Gaussian Splatting} (3D-GS) for scene reconstruction, especially in under-observed regions. An iterative feedback loop lets 3D geometry and 2D view synthesis inform each other, improving both the scene reconstruction and the generated views. The result is coherent, high-fidelity renderings from sparse inputs \emph{without any scene-specific training or fine-tuning}. On LLFF, DTU, DL3DV, and MipNeRF-360, our method significantly outperforms strong 3D-GS baselines under extreme sparsity.
title Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2511.17932