SeeGroup：通过自确定分组实现透明表面的多层深度估计
SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping
针对透明表面深度歧义问题，提出循环分解模块和基于强度的多层深度公式，可直接用于透明物体操作、场景重建等需要多层深度信息的视觉任务。
原文依据 We propose a multi-layer depth estimation method, SeeGroup, consisting of novel recurrent decomposition module design and an intensity-based formulation for multi-layer depth.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论透明物体在日常生活中很常见，理解它们的多层深度信息（包括透明表面及其后面的物体）对于与透明材料交互的现实应用至关重要。然而，现有的深度方法仅生成单张深度图，这对于透明表面本质上存在歧义。在本工作中，我们提出了一种多层深度估计方法SeeGroup，包含新颖的循环分解模块设计以及基于强度的多层深度公式。实验表明，我们的方法显著提升了多层深度估计的最先进水平，在LayeredDepth基准上四元组相对深度准确率从61.34%提升至70.09%。
英文原文摘要 767 字符
Transparent objects are common in daily life, and understanding their multi-layer depth information, including both the transparent surface and the objects behind it, is crucial for real-world applications that interact with transparent materials.However, existing depth methods produce only a single depth map, which is inherently ambiguous for transparent surfaces.In this work, We propose a multi-layer depth estimation method, SeeGroup, consisting of novel recurrent decomposition module design and an intensity-based formulation for multi-layer depth. Experiments demonstrate that our method significantly improves the state of the art of multi-layer depth estimation, improving quadruplet relative depth accuracy on LayeredDepth benchmark from 61.34% to 70.09%.