无需姿态，无问题：从未姿态多视角视频中馈送动态高斯
No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
AI总结：
本文提出NoPo4D，一种首个无需姿态的馈送式系统，能够处理动态内容、多视角输入和未知相机姿态，通过速度分解和双向运动编码提升性能，优于现有方法。
摘要：
近期的馈送式3D高斯散射方法在3D场景重建的单个方面取得了显著进展，但现有方法无法在单次馈送过程中同时处理动态内容、多视角输入和未知相机姿态。处理动态的 方法要么需要准确的相机姿态，要么只能接受单目输入；无姿态多视角方法仅能处理静态场景；而每场景优化方法在填补这些差距时，每场景的成本为分钟到小时。我们引入NoPo4D，首个馈送式系统，通过预训练的几何骨干网络和最近的4D高斯框架，引入速度分解，将高斯运动分解为每个像素图像平面位移和深度变化，从而可以直接从伪地面真实光流获得2D组件的监督。这规避了可微渲染将先验姿态方法与姿态准确性耦合以及先验无姿态方法所需的3D运动地面真实。系统还通过双向运动编码实现跨视角和跨帧特征聚合，以及视图依赖的不透明度，以缓解跨视角和跨时间步的高斯错位。在四个多视角动态基准上，NoPo4D一致优于现有馈送式基线，并通过可选后优化阶段超越每场景优化方法，同时运行速度快十倍。
英文摘要：
Recent feed-forward 3D gaussian splatting methods have made dramatic progress on individual aspects of 3D scene reconstruction, but no existing method jointly addresses dynamic content, multi-view input, and unknown camera poses in a single feed-forward pass. Methods that handle dynamics either require accurate camera poses or accept only monocular input; pose-free multi-view methods address only static scenes; and per-scene optimization methods bridge some of these gaps but at minutes-to-hours cost per scene. We introduce NoPo4D, the first feed-forward system that addresses this empty quadrant. Building on a pretrained geometry backbone and recent 4D Gaussian frameworks, NoPo4D introduces a velocity decomposition that splits Gaussian motion into per-pixel image-plane shifts and depth changes, allowing direct supervision from pseudo ground-truth optical flow on the 2D component. This sidesteps both the differentiable rendering that couples prior posed methods to pose accuracy and the 3D motion ground truth that prior pose-free methods require. The system is rounded out by a bidirectional motion encoder for cross-view and cross-frame feature aggregation, and view-dependent opacity that mitigates cross-view and cross-timestep Gaussian misalignments. On four multi-view dynamic benchmarks, NoPo4D consistently outperforms prior feed-forward baselines, and with an optional post-optimization stage surpasses per-scene optimization methods, while running orders of magnitude faster.
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。
