轻量级立体匹配框架，零样本泛化能力强。
LiteMatch: Lightweight Zero-Shot Stereo Matching via Cost Volume Stabilization
- 通过成本体积稳定化避免复杂3D卷积，提升效率。
- 在多个数据集上达到竞争性误差和精度，参数仅336万至958万。
- 适合资源受限场景的实时立体匹配应用。
尽管基于学习的立体匹配进展迅速，但高精度通常依赖于庞大的主干网络和计算密集的3D成本体积处理，导致显著的内存与运行时开销。更严重的是，这些方法在跨域泛化方面表现不佳，限制了实际部署。本文提出LiteMatch，一种轻量级立体匹配框架，通过成本体积稳定化实现强零样本泛化，无需昂贵的3D卷积。LiteMatch采用两个互补编码器：跨视图对应编码器（CVCE）捕捉全局跨视图交互，高频编码器（HFE）利用FFT频率线索增强细粒度结构细节。为稳定成本体积，引入体素级二元交叉熵损失（CVC-Loss），作用于softmax归一化的成本分布，促使差异概率分布尖锐且单峰，从而提升稳定性并加速收敛。一个轻量级精修模块以低迭代次数生成清晰全分辨率视差图，避免重型递归精修。模型参数量灵活，范围为336万至958万，在Scene Flow、KITTI、Middlebury、ETH3D和DrivingStereo等多个数据集上均取得具有竞争力的端点误差（EPE）和D1性能。结果表明，轻量级架构可在不牺牲准确性的前提下实现跨域泛化。
原文摘要 · Abstract (English)
Despite rapid progress in learning-based stereo matching, high accuracy is often achieved at the cost of heavy backbones and computationally intensive 3D cost volume processing, resulting in substantial memory and runtime overhead. More critically, these methods frequently struggle to generalize across domains, limiting their practical deployment. We present \textit{LiteMatch}, a lightweight stereo matching framework that achieves strong zero-shot generalization through cost volume stabilization-without expensive 3D convolutions. LiteMatch employs two complementary encoders: a Cross-View Correspondence Encoder (CVCE) to capture global cross-view interactions, and a High-Frequency Encoder (HFE) that enhances fine structural details via FFT-based frequency cues. To stabilize the cost volume, we introduce the \textit{Cost Volume Consistency Loss (CVC-Loss)}, a voxel-wise binary cross-entropy objective applied to softmax-normalized cost distributions. By encouraging sharp and unimodal disparity probabilities, CVC-Loss promotes stable cost distributions and enables rapid convergence. A lightweight refinement module further produces sharp full-resolution disparities with low-iteration updates, avoiding heavy recurrent refinement. With a flexible design ranging from 3.36M to 9.58M parameters, LiteMatch achieves exceptional zero-shot generalization, delivering competitive EPE and D1 performance across Scene Flow, KITTI, Middlebury, ETH3D, and DrivingStereo. Our results establish that lightweight architectures can indeed generalize across domains without sacrificing accuracy. \href{https://mdraqibkhan.github.io/Litematch}{\textcolor{blue}{Code}}
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。