{"ID":2838197,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17932","arxiv_id":"2511.17932","title":"Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2511.17932","url_pdf":"https://arxiv.org/pdf/2511.17932v1","authors":"[\"Yan Xu\",\"Yixing Wang\",\"Stella X. Yu\"]","published":"2025-11-22T06:08:29Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.GR\"]","methods":"[\"Diffusion Model\"]","has_code":false}