Recent works have explored the fundamental role of depth estimation in multi-view stereo (MVS) and semantic scene completion (SSC). They generally construct 3D cost volumes to explore geometric correspondence in depth, and estimate such volumes in a single step relying directly on the ground truth approximation. However, such problem cannot be thoroughly handled in one step due to complex empirical distributions, especially in challenging regions like occlusions, reflections, etc. In this paper, we formulate the depth estimation task as a multi-step distribution approximation process, and introduce a new paradigm of modeling the Volumetric Probability Distribution progressively (step-by-step) following a Markov chain with Diffusion models (VPDD). Specifically, to constrain the multi-step generation of volume in VPDD, we construct a meta volume guidance and a confidence-aware contextual guidance as conditional geometry priors to facilitate the distribution approximation. For the sampling process, we further investigate an online filtering strategy to maintain consistency in volume representations for stable training. Experiments demonstrate that our plug-and-play VPDD outperforms the state-of-the-arts for tasks of MVS and SSC, and can also be easily extended to different baselines to get improvement. It is worth mentioning that we are the first camera-based work that surpasses LiDAR-based methods on the SemanticKITTI dataset.

翻译：近期研究探讨了深度估计在多视角立体（MVS）和语义场景补全（SSC）中的基础作用。这些方法通常构建三维代价体来探索深度方向的几何对应关系，并依赖直接对真实值的近似一步估计这些体积。然而，由于复杂经验分布的存在，尤其在遮挡、反射等挑战性区域，此类问题难以通过单一步骤彻底解决。本文中，我们将深度估计任务建模为多步分布逼近过程，并引入一种新范式：利用扩散模型沿马尔可夫链逐步（逐步骤）建模体积概率分布（VPDD）。具体而言，为约束VPDD中体积的多步生成，我们构建了元体积引导和置信度感知上下文引导作为条件几何先验，以促进分布逼近。在采样过程中，我们进一步研究了一种在线滤波策略，以保持体积表示的一致性，实现稳定训练。实验表明，我们的即插即用型VPDD在MVS和SSC任务上均优于现有最先进方法，并可轻松扩展至不同基线模型以获得性能提升。值得提及的是，我们是首个在SemanticKITTI数据集上超越基于激光雷达方法的纯相机视觉工作。