解决长序列3D重建中的尺度漂移问题，提升全局几何一致性。
VGGT-Align: Bridging Local Reconstruction and Global Consistency for Long-Sequence 3D Reconstruction
- 利用环境几何不变量建立跨片段尺度约束，抑制误差累积。
- 在多个基准上将绝对轨迹误差降低32%，显著提升重建稳定性。
- 无需重训练的即插即用模块，适合长期动态场景重建任务。
长序列3D重建中保持全局几何一致性是核心挑战，尺度漂移是最严重的失效模式。在分块推理流程中，序列Sim(3)对齐存在尺度自由度未受约束的问题，导致估计误差呈乘积式累积，扭曲全局轨迹与点云结构。本文提出基于关键洞察的尺度一致性增强框架：在如驾驶场景等结构化环境中，由环境规律产生的几何量在时间片段间具有固有不变性，其分段测量值的差异可直接暴露跨片段尺度漂移。我们提出场景几何不变量锚定（SGIA），通过粗到细的鲁棒估计从每块预测点云中提取主导几何不变量，并利用其跨片段一致性建立独立于点云配准的尺度约束，将7-DoF Sim(3)对齐显式降为6-DoF刚体变换，从源头切断链式尺度误差传播。此外引入轻量级测试时自适应策略，仅通过多目标自监督微调归一化层参数，逐步改进序列内各块预测。两个模块均为即插即用设计，无需离线重训练。在多个长序列基准上实验表明，本方法达到当前最优性能，绝对轨迹误差最高降低32%，显著提升轨迹稳定性和重建质量。代码见：https://github.com/WZ-CS/VGGT-Align
原文摘要 · Abstract (English)
Maintaining global geometric consistency is a central challenge in long-sequence 3D reconstruction, with scale drift being the most critical failure mode. In chunk-based inference pipelines, the scale degree of freedom in sequential Sim(3) alignment is left unconstrained, causing estimation errors to compound multiplicatively and distort global trajectories and point cloud geometry. We present a scale-consistency enhancement framework built on a key insight: in structured environments such as driving scenes, geometric quantities arising from environmental regularity remain inherently invariant across temporal segments, and discrepancies in their per-chunk measurements directly expose inter-chunk scale drift. We propose Scene Geometric Invariant Anchoring (SGIA), which extracts dominant geometric invariants from each chunk's predicted point cloud via coarse-to-fine robust estimation and exploits their cross-chunk consistency to establish scale constraints independent of point cloud registration, explicitly degenerating 7-DoF Sim(3) alignment into 6-DoF rigid-body transformation and severing chain-wise scale error propagation at its source. We further introduce a lightweight test-time adaptation strategy that fine-tunes only normalization-layer parameters via multi-objective self-supervision, progressively improving intra-chunk predictions along the sequence. Both modules are plug-and-play and require no offline retraining. Experiments on multiple long-sequence benchmarks demonstrate state-of-the-art performance, reducing absolute trajectory error by up to 32% with significant gains in trajectory stability and reconstruction quality. Code: https://github.com/WZ-CS/VGGT-Align
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。