GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assembly

2026-08-18

AI Summary

为解决长序列3D重建中的几何精度和全局一致性问题，GeoWeaver通过几何先验模型和测试时适应方法优化了相机姿态、深度修正和内在参数。

Abstract

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.

Problem

• Long-sequence 3D Reconstruction
• Camera Motion
• Geometric Accuracy

Innovation

• Geometric Prior Model (GPM)
• Test-Time Adaptation (TTA)
• Sequential Initialization
• Global Chunk-Level Sim(3) Alignment
• Coarse-to-Fine Refinement