统一动态环境下的单目位姿估计，兼顾鲁棒性与精度。
WildPose: A Unified Framework for Robust Pose Estimation in the Wild
- 融合前馈模型感知与可微分优化，构建3D感知更新机制。
- 在动态（Wild-SLAM）、静态（TUM）和低运动（Sintel）数据集上均领先。
- 适合需要高鲁棒性的实时定位与建图场景。
在动态环境中估计相机位姿是关键挑战，因多数视觉SLAM与SfM方法假设场景静止。现有动态感知方法多不统一：基于语义的方法脆弱，逐序列优化对短序列失效，其他学习模型在纯静态场景中性能下降。本文提出WildPose，一种统一的单目位姿估计框架，在动态环境中保持鲁棒性的同时，在静态与低自身运动数据集上达到顶尖性能。核心思想是结合现代3D视觉中两大强大范式：前馈模型的丰富感知前端与可微分束调整（BA）的端到端优化。通过基于冻结预训练MASt3R特征主干的3D感知更新算子，以及利用同一主干的多层级3D感知特征的高容量运动掩码检测器实现。大量实验表明，WildPose在动态（Wild-SLAM、Bonn）、静态（TUM、7-Scenes）和低自身运动（Sintel）基准上持续优于现有方法。
原文摘要 · Abstract (English)
Estimating camera pose in dynamic environments is a critical challenge, as most visual SLAM and SfM methods assume static scenes. 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 may degrade 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 two powerful paradigms in modern 3D vision: the rich perceptual frontend of feedforward models and the end-to-end optimization of differentiable bundle adjustment (BA). We achieve this with a 3D-aware update operator built on a frozen, pre-trained MASt3R feature backbone, together with a high-capacity motion mask detector that uses multi-level 3D-aware features from the same backbone. Extensive experiments show WildPose consistently outperforms prior methods across dynamic (Wild-SLAM, Bonn), static (TUM, 7-Scenes), and low-ego-motion (Sintel) benchmarks.
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。