UniScale：通过先验注入实现多视角理解的统一尺度感知3D重建
UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception
AI总结：
UniScale通过整合几何先验实现多视角下的统一尺度感知3D重建，适用于机器人感知任务。
摘要：
我们提出了UniScale，一种统一的、尺度感知的多视角3D重建框架，用于机器人应用，通过模块化、语义引导的设计灵活整合几何先验。在基于视觉的机器人导航中，从原始图像序列中准确提取环境结构对后续任务至关重要。UniScale通过一个单一的前馈网络联合估计相机内参和外参、尺度不变的深度和点图以及场景的度量尺度，同时可选地整合辅助几何先验。通过结合全局上下文推理与相机感知的特征表示，UniScale能够恢复场景的度量尺度。在相机内参已知的机器人环境中，它们可以轻松地被整合以提高性能，当相机姿态也可用时，还能获得额外的增益。这种联合设计使单一统一模型能够实现鲁棒、度量感知的3D重建。重要的是，UniScale不需要从头开始训练，并利用现有模型中展现的world priors，而无需几何编码策略，使其特别适合资源受限的机器人团队。我们在多个基准上评估了UniScale，展示了强大的泛化能力和在多样环境中的稳定性能。我们将在接受后发布我们的实现。
英文摘要：
We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors through a modular, semantically informed design. In vision-based robotic navigation, the accurate extraction of environmental structure from raw image sequences is critical for downstream tasks. UniScale addresses this challenge with a single feed-forward network that jointly estimates camera intrinsics and extrinsics, scale-invariant depth and point maps, and the metric scale of a scene from multi-view images, while optionally incorporating auxiliary geometric priors when available. By combining global contextual reasoning with camera-aware feature representations, UniScale is able to recover the metric-scale of the scene. In robotic settings where camera intrinsics are known, they can be easily incorporated to improve performance, with additional gains obtained when camera poses are also available. This co-design enables robust, metric-aware 3D reconstruction within a single unified model. Importantly, UniScale does not require training from scratch, and leverages world priors exhibited in pre-existing models without geometric encoding strategies, making it particularly suitable for resource-constrained robotic teams. We evaluate UniScale on multiple benchmarks, demonstrating strong generalization and consistent performance across diverse environments. We will release our implementation upon acceptance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
