PromptStereo：通过结构与运动提示词实现零样本立体匹配
PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts
将单目深度基础模型的解码器改造为提示词引导的迭代细化模块（PRU），把单目结构线索与立体运动线索作为提示词注入潜变量，为立体匹配的迭代阶段提供可复用的零样本泛化增强手段。
原文依据 we propose Prompt Recurrent Unit (PRU), a novel iterative refinement module based on the decoder of monocular depth foundation models
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现代立体匹配方法利用单目深度基础模型实现了优越的零样本泛化性能。然而，大多数现有方法主要关注为代价体构建或视差初始化提取鲁棒特征。与此同时，对零样本泛化同样至关重要的迭代细化阶段却研究不足。一些方法将单目深度先验作为迭代的引导，但传统的基于 GRU 的架构由于表示能力有限而难以充分利用这些先验。本文提出提示循环单元（Prompt Recurrent Unit, PRU），一种基于单目深度基础模型解码器的新型迭代细化模块。通过将单目结构线索和立体运动线索作为提示词集成到解码器中，PRU 在保留单目深度基础模型固有单目深度先验的同时，为其潜变量表示丰富了绝对立体尺度信息。实验表明，我们的 PromptStereo 在多个数据集上实现了最优的零样本泛化性能，同时保持相当或更快的推理速度。我们的发现凸显了提示词引导的迭代细化作为零样本立体匹配一个有前景的方向。
英文原文摘要 1290 字符
Modern stereo matching methods have leveraged monocular depth foundation models to achieve superior zero-shot generalization performance. However, most existing methods primarily focus on extracting robust features for cost volume construction or disparity initialization. At the same time, the iterative refinement stage, which is also crucial for zero-shot generalization, remains underexplored. Some methods treat monocular depth priors as guidance for iteration, but conventional GRU-based architectures struggle to exploit them due to the limited representation capacity. In this paper, we propose Prompt Recurrent Unit (PRU), a novel iterative refinement module based on the decoder of monocular depth foundation models. By integrating monocular structure and stereo motion cues as prompts into the decoder, PRU enriches the latent representations of monocular depth foundation models with absolute stereo-scale information while preserving their inherent monocular depth priors. Experiments demonstrate that our PromptStereo achieves state-of-the-art zero-shot generalization performance across multiple datasets, while maintaining comparable or faster inference speed. Our findings highlight prompt-guided iterative refinement as a promising direction for zero-shot stereo matching.