Reliev3R: 从多视角几何注释中解脱的前馈重建
Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations
AI总结：
Reliev3R通过弱监督方法训练前馈重建模型，无需昂贵的多视角几何注释，利用单目相对深度和图像稀疏对应关系进行3D知识学习，提升重建效率与可扩展性。
摘要：
随着近期进展，前馈重建模型（FFRMs）在重建质量和适应多种下游任务方面展现出巨大潜力。然而，过度依赖多视角几何注释（如3D点云和相机姿态）使FFRMs的全监督训练方案难以扩展。本文提出Reliev3R，一种弱监督方法，用于从头训练FFRMs，而无需昂贵的多视角几何注释。通过减少对几何传感数据和计算密集型结构从运动预处理的依赖，我们的方法直接从单目相对深度和预训练模型的零样本预测提供的稀疏对应关系中获取3D知识。Reliev3R的核心是设计了意识模糊的相对深度损失和基于三角学的重投影损失，以促进多视角几何一致性监督。在较少数据下训练，Reliev3R与全监督模型持平，朝着低成本3D重建监督和可扩展的FFRMs迈进。
英文摘要：
With recent advances, Feed-forward Reconstruction Models (FFRMs) have demonstrated great potential in reconstruction quality and adaptiveness to multiple downstream tasks. However, the excessive reliance on multi-view geometric annotations, e.g. 3D point maps and camera poses, makes the fully-supervised training scheme of FFRMs difficult to scale up. In this paper, we propose Reliev3R, a weakly-supervised paradigm for training FFRMs from scratch without cost-prohibitive multi-view geometric annotations. Relieving the reliance on geometric sensory data and compute-exhaustive structure-from-motion preprocessing, our method draws 3D knowledge directly from monocular relative depths and image sparse correspondences given by zero-shot predictions of pretrained models. At the core of Reliev3R, we design an ambiguity-aware relative depth loss and a trigonometry-based reprojection loss to facilitate supervision for multi-view geometric consistency. Training from scratch with the less data, Reliev3R catches up with its fully-supervised sibling models, taking a step towards low-cost 3D reconstruction supervisions and scalable FFRMs.
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。
