深度假设引导的迭代细化用于事件-图像单目深度估计
Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimation
把连续深度回归转成基于离散深度假设体积的约束搜索，并用轻量多尺度相关代价体积做全局到局部的迭代残差细化，这一思路可直接迁移到其他病态回归任务（如光流、法向、表面重建）以及事件-图像融合的稠密预测中。
原文依据 we construct a 3D cost volume between the DHV features and contextual features and perform a multi-scale correlation search
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论事件相机具有优异的动态特性，在单目深度估计（MDE）方面展现出巨大潜力。然而，现有方法主要通过优化上下文特征来提升性能，仍难以应对直接全深度回归的病态与非线性本质。本文提出 HypoDepth，这是首个事件-图像单目深度迭代细化框架。通过引入离散的深度假设体积（DHV），我们将深度回归问题转化为受约束的深度搜索任务。具体而言，我们构建 DHV 特征与上下文特征之间的三维代价体积，并执行多尺度相关性搜索以引导稳定的残差优化。该轻量级代价体积能够在多分辨率下实现高效的全局到局部细化。我们的方法在 DSEC 和 MVSEC 上取得最优结果，并具有强大的零样本泛化能力。同时，我们的微型模型在精度与效率之间取得出色平衡，可在资源受限设备上实现实时性能。
英文原文摘要 1087 字符
Event cameras hold excellent dynamic properties, showing great potential for monocular depth estimation (MDE). However, existing methods mainly improve performance by optimizing contextual features, but still struggle with the ill-posed and nonlinear nature of direct full-depth regression. In this paper, we propose HypoDepth, the first event-image monocular depth iterative refinement framework. By introducing a discrete Depth Hypothesis Volume (DHV), we transform the depth regression problem into a constrained depth search task. Specifically, we construct a 3D cost volume between the DHV features and contextual features and perform a multi-scale correlation search to guide stable residual optimization. This lightweight cost volume enables efficient global-to-local refinement across multi-resolution. Our method outperforms existing approaches on DSEC and MVSEC with state-of-the-art results and strong zero-shot generalization. Meanwhile, our tiny model achieves an excellent balance between accuracy and efficiency, enabling real-time performance on resource-limited devices.