实时重建无姿态图像的3D高斯点云，渲染质量接近离线方法。
OF$^3$GS: On-the-Fly Feed-Forward 3D Gaussian Splatting from Unposed Images
- 分步解耦内参与场景尺度，减少累积误差。
- 动态点偏移补偿相机位姿与深度漂移问题。
- 适合移动端或实时应用，内存占用低。
前馈式3D高斯点阵（3DGS）可从离线图像序列实现高效高保真新视角合成（NVS）。然而，从无姿态图像中实现实时NVS仍具挑战：系统需在图像到达时即时重建可渲染的3D高斯点，且无法访问未来观测。尽管已有在线前馈几何方法用于因果深度和点云恢复，直接将其应用于NVS常导致严重渲染伪影，因高斯渲染对多视角一致性要求更高，尤其在点尺寸和位姿-几何对齐方面。微小偏差在因果推理下会累积并显著降低渲染质量。为此，我们提出OF$^3$GS，一种在因果约束下从稀疏视角无姿态图像实现高效高质量实时NVS的前馈框架。引入两项机制保障因果几何稳定性：解耦的内在参数恢复头，缓解累积相机内参偏差与场景尺度抖动；动态点精修偏移，放松刚性反投影以补偿耦合的位姿-深度漂移。大量实验表明，OF$^3$GS优于现有在线基线，在相似稀疏输入条件下逼近离线前馈3DGS性能，且在更密集输入下仍保持内存可行性。
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。