GeoWeaver：通过分层几何组装实现精准长序列三维重建
GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assembly
浏览论文内容
中文总结 AI 辅助
GeoWeaver是含GPM与TTA的统一框架，通过分层几何组装解决长序列3D重建的尺度漂移等问题，提升全局一致性，且可适配不同几何先验模型。
中文摘要 AI 辅助
从RGB视频进行长序列三维重建，既需要精准的局部几何结构，也需要全局一致的相机运动。前馈模型能提供可靠的深度和位姿预测，但其内存开销阻碍了对长序列的联合推理。分块处理提升了可扩展性，但独立预测的分块常出现尺度漂移、位姿误差和点云错位。我们提出GeoWeaver，这是一个包含几何先验模型（GPM）和测试时自适应（TTA）的统一框架。GPM可预测分块级深度、置信度和相机参数，作为可调整的几何先验；TTA则执行顺序初始化、全局分块级Sim(3)对齐，以及相机位姿、仿射深度校正和内参的由粗到细优化。密集对应关系提供相邻、跨分块和长程约束，而鲁棒的CDF式目标函数联合优化加权2D重投影与3D一致性残差。该设计在保留局部几何精度的同时，纠正累积的位姿、尺度、深度和校准误差。在各类长序列基准上的实验表明，该方法提升了相机精度、全局一致性和点云质量； ablation实验验证了各自适应阶段的贡献，且将相同TTA流程应用于不同几何先验模型时，均能持续改进其轨迹估计，证明GeoWeaver不依赖特定的GPM。
英文摘要
Long-sequence 3D reconstruction from RGB videos requires both accurate local geometry and globally consistent camera motion. Feed-forward models provide strong depth and pose predictions, but their memory cost prevents joint inference over long sequences. Chunk-wise processing improves scalability, yet independently predicted chunks often exhibit scale drift, pose errors, and point-cloud misalignment. We present GeoWeaver, a unified framework comprising a Geometric Prior Model (GPM) and Test-Time Adaptation (TTA). The GPM predicts chunk-wise depth, confidence, and camera parameters as adjustable geometric priors. TTA then performs sequential initialization, global chunk-level Sim(3) alignment, and coarse-to-fine refinement of camera poses, affine depth corrections, and intrinsics. Dense correspondences provide adjacent, cross-chunk, and long-range constraints, while a robust CDF-style objective jointly optimizes weighted 2D reprojection and 3D consistency residuals. This design preserves local geometric accuracy while correcting accumulated pose, scale, depth, and calibration errors. Experiments across diverse long-sequence benchmarks demonstrate improved camera accuracy, global consistency, and point-cloud quality. Ablations verify the contribution of each adaptation stage, and applying the same TTA procedure to different geometric prior models consistently improves their trajectory estimates, demonstrating that GeoWeaver is not tied to a specific GPM.
