发表机构
BRAC University; Mahidol University（布拉卡大学; 玛希隆大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对前馈3D重建中无训练扰动不确定性受对称性影响的问题，提出ReVar3R，通过规范感知配准计算逐点方差，无需重训练，在多个骨干和数据集上优于内置置信度。
AI 中文摘要
一个正确重建的远距离点，即使冻结的3D模型处理等效输入，也会显得不确定，因为其输出帧会旋转一个微小角度。这暴露了无训练扰动不确定性的弱点：当输出包含未观察到的对称性时，运行间的变化可能反映对称性而非误差。现有替代方案存在权衡：内置置信度在大多数评估条件下表现不佳，而训练的证据头需要特定于模型的监督。对于点图，本研究推导出一个闭式、与误差无关的方差项，该项随场景范围增长，并可能淹没期望的信号。模拟重现了该效应；所有30个真实VGGT视图集均表现出其预测的$\\|x_p\\|^2$特征。ReVar3R在计算逐点方差之前，将预测稳健地配准到公共相似性框架，无需重新训练或修改冻结模型。可选的校准和融合使用留出分割。在VGGT、$\pi$3和MASt3R上，跨六个数据集，同一估计器在每个骨干网络上，在18个条件中的15个条件下将AUSE降至内置置信度以下。分阶段评估产生：无标签核心11/18胜，无标签等权融合12/18胜，留出权重14/18胜，包含内置信号时15/18胜。与训练的证据头相比，结果是一种权衡：证据头更好地校准幅度并在其训练领域领先，而ReVar3R无需适应即可跨骨干网络迁移。其排序改善了点过滤，但不检测稳定的系统性偏差，不辅助新视图合成，也不跨领域迁移校准。
英文摘要
A correctly reconstructed distant point appears uncertain even when a frozen 3D model processes equivalent inputs because its output frame rotates fractionally. This exposes a weakness of trainingfree perturbation uncertainty: when outputs contain an unobserved symmetry, run-to-run variation potentially reflects symmetry rather than error. Existing alternatives have trade-offs: built-in confidence is outperformed in most evaluated conditions, while trained evidential heads require modelspecific supervision. For point maps, this research derives a closed-form, error-independent variance term that grows with scene extent and potentially overwhelms the desired signal. Simulation reproduces the effect; all 30 real VGGT view-sets tested exhibit its predicted $\|x_p\|^2$ signature. ReVar3R robustly registers predictions to a common similarity frame before computing per-point variance, without retraining or modifying the frozen model. Optional calibration and fusion use a held-out split. Across VGGT, π3, and MASt3R on six datasets, the same estimator on every backbone lowers AUSE below built-in confidence in 15 of 18 conditions. The staged evaluation yields 11 of 18 wins for the label-free core, 12/18 for label-free equal-weight fusion, 14/18 with held-out weights, and 15/18 when the built-in signal is included. Against a trained evidential head, the result is a trade-off: the head calibrates magnitude better and leads in its training domain, whereas ReVar3R transfers across backbones without adaptation. Its ranking improves point filtering, but it does not detect stable systematic bias, aid novel-view synthesis, or transfer calibration across domains.
