Image-guided depth completion aims at generating a dense depth map from sparse LiDAR data and RGB image. Recent methods have shown promising performance by reformulating it as a classification problem with two sub-tasks: depth discretization and probability prediction. They divide the depth range into several discrete depth values as depth categories, serving as priors for scene depth distributions. However, previous depth discretization methods are easy to be impacted by depth distribution variations across different scenes, resulting in suboptimal scene depth distribution priors. To address the above problem, we propose a progressive depth decoupling and modulating network, which incrementally decouples the depth range into bins and adaptively generates multi-scale dense depth maps in multiple stages. Specifically, we first design a Bins Initializing Module (BIM) to construct the seed bins by exploring the depth distribution information within a sparse depth map, adapting variations of depth distribution. Then, we devise an incremental depth decoupling branch to progressively refine the depth distribution information from global to local. Meanwhile, an adaptive depth modulating branch is developed to progressively improve the probability representation from coarse-grained to fine-grained. And the bi-directional information interactions are proposed to strengthen the information interaction between those two branches (sub-tasks) for promoting information complementation in each branch. Further, we introduce a multi-scale supervision mechanism to learn the depth distribution information in latent features and enhance the adaptation capability across different scenes. Experimental results on public datasets demonstrate that our method outperforms the state-of-the-art methods. The code will be open-sourced at [this https URL](https://github.com/Cisse-away/PDDM).

翻译：图像引导的深度补全旨在从稀疏LiDAR数据和RGB图像生成稠密深度图。最新方法通过将其重构为包含深度离散化和概率预测两个子任务的分类问题，展现出优异性能。该类方法将深度范围划分为若干离散深度值作为深度类别，为场景深度分布提供先验信息。然而，现有深度离散化方法易受不同场景深度分布变化的影响，导致次优的场景深度分布先验。针对上述问题，我们提出渐进式深度解耦与调制网络，该网络通过多阶段渐进式地将深度范围解耦为区间，并自适应生成多尺度稠密深度图。具体而言，我们首先设计区间初始化模块（Bins Initializing Module, BIM），通过探索稀疏深度图内的深度分布信息构建种子区间，以适应深度分布变化。随后建立渐进式深度解耦分支，从全局到局部逐步细化深度分布信息。同时，开发自适应深度调制分支，从粗粒度到细粒度逐步优化概率表示。并引入双向信息交互机制，加强两个分支（子任务）间的信息交互，促进各分支信息互补。进一步，我们提出多尺度监督机制，学习潜在特征中的深度分布信息，增强跨场景适应能力。在公开数据集上的实验结果表明，本方法优于当前最先进方法。代码将开源至[此https链接](https://github.com/Cisse-away/PDDM)。