Online3R：基于几何基础模型的在线学习一致序列重建
Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Model
将轻量可学习视觉提示注入冻结的几何基础模型，并通过局部-全局自监督一致性约束在测试时在线更新，为视觉中的序列重建提供了一种无需真值的高效自适应方案。
原文依据 we introduce a set of learnable lightweight visual prompts into a pretrained, frozen geometry foundation model
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 Online3R，一种新的序列重建框架，能够通过在线学习适应新场景，有效解决不一致性问题。具体而言，我们向预训练且冻结的几何基础模型中引入一组可学习的轻量视觉提示，以捕获新环境的知识，同时保持基础模型进行几何预测的基本能力。为了解决测试时更新这些视觉提示时缺少真值和高效率要求的问题，我们引入一种局部-全局自监督学习策略，通过对预测施加局部和全局一致性约束来实现。局部一致性约束在中间结果和先前局部融合结果上进行，使模型能够利用高质量的伪真值信号进行训练；全局一致性约束在跨越长距离的稀疏关键帧而非每帧上操作，使模型能够以高效的方式从长轨迹上的一致预测中学习。我们的实验表明，Online3R 在各种基准上优于先前的最优方法。项目页面：https://shunkaizhou.github.io/online3r-1.0/
英文原文摘要 1269 字符
We present Online3R, a new sequential reconstruction framework that is capable of adapting to new scenes through online learning, effectively resolving inconsistency issues. Specifically, we introduce a set of learnable lightweight visual prompts into a pretrained, frozen geometry foundation model to capture the knowledge of new environments while preserving the fundamental capability of the foundation model for geometry prediction. To solve the problems of missing groundtruth and the requirement of high efficiency when updating these visual prompts at test time, we introduce a local-global self-supervised learning strategy by enforcing the local and global consistency constraints on predictions. The local consistency constraints are conducted on intermediate and previously local fused results, enabling the model to be trained with high-quality pseudo groundtruth signals; the global consistency constraints are operated on sparse keyframes spanning long distances rather than per frame, allowing the model to learn from a consistent prediction over a long trajectory in an efficient way. Our experiments demonstrate that Online3R outperforms previous state-of-the-art methods on various benchmarks. Project page: https://shunkaizhou.github.io/online3r-1.0/