Abstract
While iterative stereo matching achieves high accuracy, its dependence on Recurrent Neural Networks (RNN) hinders edge deployment, a challenge underexplored in existing researches. We analyze iterative refinement and reveal that disparity updates are spatially sparse and temporally redundant. First, we introduce a progressive iteration pruning strategy that suppresses redundant update steps, effectively collapsing the recursive computation into a near-single-pass inference. Second, we propose a collaborative monocular prior transfer framework that implicitly embeds depth priors without requiring a dedicated monocular encoder, thereby eliminating its associated computational burden. Third, we develop FlashGRU, a hardware-aware RNN operator leveraging structured sparsity and I/O-conscious design, achieving a 7.28$\times$ speedup, 76.6\% memory peak reduction and 80.9\% global memory requests reduction over natvie ConvGRUs under 2K resolution. Our PipStereo enables real-time, high-fidelity stereo matching on edge hardware: it processes 320$\times$640 frames in just 75ms on an NVIDIA Jetson Orin NX (FP16) and 19ms on RTX 4090, matching the accuracy of large iterative based models, and our generalization ability and accuracy far exceeds that of existing real-time methods. Our embedded AI projects will be updated at: this https URL.
Abstract (translated)
虽然迭代立体匹配方法能够实现高精度，但其对递归神经网络（RNN）的依赖阻碍了边缘设备部署这一挑战在现有研究中较少被探索。我们分析了迭代细化过程，并发现视差更新具有空间稀疏性和时间冗余性。首先，我们提出了一种渐进式迭代剪枝策略，该策略可以抑制多余的更新步骤，从而将递归计算有效简化为近似单次推理过程。其次，我们设计了一个协作的单目先验转移框架，该框架能够隐式嵌入深度先验信息，而无需专门的单目编码器，从而减轻了相应的计算负担。第三，我们开发了一种称为FlashGRU的新硬件感知RNN操作符，它利用结构化稀疏性和输入/输出意识的设计，在2K分辨率下实现了7.28倍的速度提升，峰值内存减少了76.6%，全局内存请求减少达80.9%。 我们的PipStereo方法能够在边缘设备硬件上实现实时、高保真的立体匹配：在NVIDIA Jetson Orin NX（FP16）和RTX 4090平台上分别只需要75毫秒和19毫秒即可处理320x640像素的图像帧，其精度与大型迭代方法相媲美，并且我们的泛化能力和准确性远超现有的实时方法。有关我们嵌入式AI项目的最新进展，请访问：此链接。 （请将“this https URL”替换为实际发布的网址或具体说明。）
URL
https://arxiv.org/abs/2602.20496
