WildPose：面向野外鲁棒姿态估计的统一框架
WildPose: A Unified Framework for Robust Pose Estimation in the Wild
把冻结的 MASt3R 特征骨干网络接入可微 BA 的 3D-aware 更新算子，并用同一骨干的多层级特征训练运动掩码检测器，为动态场景下的单目相机定位提供了一条可复用的「前馈感知前端 + 端到端优化」路线。
原文依据 integrating a frozen, pre-trained MASt3R feature backbone and training the operator's subsequent layers
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在动态环境中估计相机姿态是一项关键挑战，因为大多数视觉 SLAM 与 SfM 方法都假设输入来自静态环境。尽管已有一些动态感知方法，但它们往往并不统一：基于语义的方法较为脆弱，逐序列优化方法在短序列上失效，而其他学习模型有时在纯静态场景上表现不佳。我们提出 Wildpose，一个统一的单目姿态估计框架，它在动态环境中保持鲁棒，同时在静态与低自运动数据集上维持最优性能。我们的核心洞见是连接现代三维视觉中两大强大范式：前馈模型丰富的感知前端与可微光束法平差（BA）的端到端优化。我们通过两方面增强可微 BA 流程来实现这一点。第一，我们引入一个新的 3D-aware 更新算子，将冻结的预训练 MASt3R 特征骨干网络集成进来，并在静态与动态数据的多样化课程上训练该算子后续的层。第二，我们提出一个高容量运动掩码检测器，它利用来自同一冻结骨干网络的丰富多层级 3D-aware 特征。大量实验表明，Wildpose 在多种基准上持续优于先前方法，包括动态（Wild-SLAM、Bonn）、静态（TUM、7-Scenes）与低自运动（Sintel）数据集。
英文原文摘要 1415 字符
Estimating camera pose in dynamic environments is a critical challenge, as most visual SLAM and SfM methods assume inputs from static environments. While recent dynamic-aware methods exist, they are often not unified: semantic-based approaches are brittle, per-sequence optimization methods fail on short sequences, and other learned models sometimes perform badly on static-only scenes. We present Wildpose, a unified monocular pose estimation framework that is robust in dynamic environments while maintaining state-of-the-art performance on static and low-ego-motion datasets. Our key insight is to connect the two powerful paradigms in modern 3D vision: the rich perceptual frontend of feed-forward models and the end-to-end optimization of differentiable bundle adjustment (BA). We achieve this by enhancing the differentiable BA pipeline in two ways. First, we introduce a new 3D-aware update operator by integrating a frozen, pre-trained MASt3R feature backbone and training the operator's subsequent layers on a diverse curriculum of static and dynamic data. Second, we propose a high-capacity motion mask detector that leverages rich, multi-level 3D-aware features from the same frozen backbone. Extensive experiments show Wildpose consistently outperforms prior methods across a wide variety of benchmarks, including dynamic (Wild-SLAM, Bonn), static (TUM, 7-Scenes), and low-ego-motion (Sintel) datasets.