FreeStreamGS: 来自无位姿流式输入的在线前馈3D高斯泼溅
OF$^3$GS: On-the-Fly Feed-Forward 3D Gaussian Splatting from Unposed Images
AI总结：
提出FreeStreamGS，一种在线前馈框架，通过解耦内参恢复头和动态点精炼偏移策略，实现从无位姿流式输入的高效高质量新视角合成。
摘要：
前馈3D高斯泼溅（3DGS）允许从离线录制的图像序列进行高效高保真的新视角合成（NVS）。然而，从流式和无位姿图像输入实现在线NVS仍然具有挑战性。尽管已经提出了用于流式深度和点云恢复的在线前馈几何估计方法，但由于严重的渲染伪影，它们无法适应NVS。这是因为NVS对高斯尺度和位姿-几何对齐要求更严格的多视图一致性；即使微小的偏差也会随时间累积并明显降低渲染质量。为此，我们提出了FreeStreamGS，一个鲁棒的在线前馈框架，用于高效高质量的NVS。我们引入了两个关键机制：解耦内参恢复头，消除累积的相机内参偏差并防止长期流式中的场景尺度抖动；以及动态点精炼偏移策略，放松刚性反投影以校正耦合的位姿-深度漂移。大量实验表明，尽管FreeStreamGS无法访问未来帧，但其渲染质量与最先进的离线前馈3DGS方法相当。
英文摘要：
Feed-forward 3D Gaussian Splatting (3DGS) enables efficient and high-fidelity novel view synthesis (NVS) from offline image sequences. However, achieving on-the-fly NVS from unposed images remains challenging: the system must reconstruct renderable 3D Gaussians as images arrive, without access to future observations. Although online feed-forward geometry methods have been developed for causal depth and point-cloud recovery, directly adapting them to NVS often leads to severe rendering artifacts because Gaussian-based rendering demands stricter multi-view consistency in primitive scale and pose-geometry alignment. Even minor deviations can accumulate under causal inference and visibly degrade rendering quality. To this end, we propose OF$^3$GS, a feed-forward framework for efficient and high-quality on-the-fly NVS from sparse-view unposed images under causal constraints. We introduce two mechanisms for causal geometric stability: a Decoupled Intrinsic Recovery Head that mitigates cumulative camera-intrinsic bias and scene-scale jitter, and Dynamic Point Refinement Offsets that relax rigid unprojection to compensate for coupled pose-depth drift. Extensive experiments show that OF$^3$GS outperforms online baselines and approaches offline feed-forward 3DGS methods under comparable sparse-input settings. It also remains memory-feasible with denser inputs. Homepage: https://richardchen225.github.io/of3gs/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
