解锁三维视觉几何估计的关键因素之力
Unlocking the Power of Critical Factors for 3D Visual Geometry Estimation
论文通过系统性消融实验揭示了数据多样性、损失函数设计、监督对齐方式等关键因素对前馈三维几何估计的影响，并提出了结合优化方法优势的一致性损失函数和高分辨率架构设计，这些发现和设计可直接用于改进深度估计、相机位姿估计和点云重建等视觉任务。
原文依据 Experiments on point cloud reconstruction, video depth estimation, and camera pose/intrinsic estimation show that CARVE achieves strong and robust performance across diverse benchmarks.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论前馈视觉几何估计最近取得了快速进展。然而，一个重要的差距仍然存在：多帧模型通常产生更好的跨帧一致性，但它们在单帧精度上往往不如强大的逐帧方法。这一观察促使我们通过严格的消融研究系统性地探究驱动模型性能的关键因素，揭示了几个关键见解：1）扩大数据多样性和质量即使在对最优的视觉几何估计方法中也能解锁进一步的性能提升；2）常用的置信度感知损失和基于梯度的损失机制可能无意中阻碍性能；3）通过逐序列和逐帧对齐进行联合监督可以改善结果，而局部区域对齐却令人惊讶地降低了性能。此外，我们引入了两项增强措施，以整合基于优化的方法和高分辨率输入的优势：一个一致性损失函数，强制深度图、相机参数和点图之间的对齐；以及一个利用高分辨率信息的高效架构设计。我们将这些设计集成到CARVE中，这是一个用于前馈视觉几何估计的分辨率增强模型。在点云重建、视频深度估计和相机位姿/内参估计上的实验表明，CARVE在各种基准上实现了强大且稳健的性能。
英文原文摘要 1455 字符
Feed-forward visual geometry estimation has recently made rapid progress. However, an important gap remains: multi-frame models usually produce better cross-frame consistency, yet they often underperform strong per-frame methods on single-frame accuracy. This observation motivates our systematic investigation into the critical factors driving model performance through rigorous ablation studies, which reveals several key insights: 1) Scaling up data diversity and quality unlocks further performance gains even in state-of-the-art visual geometry estimation methods; 2) Commonly adopted confidence-aware loss and gradient-based loss mechanisms may unintentionally hinder performance; 3) Joint supervision through both per-sequence and per-frame alignment improves results, while local region alignment surprisingly degrades performance. Furthermore, we introduce two enhancements to integrate the advantages of optimization-based methods and high-resolution inputs: a consistency loss function that enforces alignment between depth maps, camera parameters, and point maps, and an efficient architectural design that leverages high-resolution information. We integrate these designs into CARVE, a resolution-enhanced model for feed-forward visual geometry estimation. Experiments on point cloud reconstruction, video depth estimation, and camera pose/intrinsic estimation show that CARVE achieves strong and robust performance across diverse benchmarks.