发表机构
Robotics Research Center (RRC), IIIT Hyderabad（海得拉巴国际信息技术研究所机器人研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究透明表面深度估计难题，提出SILICA统一管道，利用文本到图像扩散模型先验联合预测玻璃分割和深度，无需真实世界玻璃深度注释，经实验验证其在不同环境中零样本转移性能出色，优于现有模型。
AI 中文摘要
标准深度传感器在透明表面上会系统性失败，导致3D地图损坏和严重导航危险。基于学习的单目深度估计成为替代方案，但特定领域的玻璃感知单目深度估计器在不熟悉的室内布局中存在问题，且受真实世界玻璃深度注释稀缺限制。为此探索文本到图像扩散模型的先验能否实现对透明表面的泛化感知。引入SILICA统一管道，利用这些先验联合预测玻璃分割和玻璃感知深度，消除对配对真实世界玻璃深度注释的需求。使用预测的分割掩码过滤标准传感器中不正确的玻璃深度点，为下游3D映射和自主防撞恢复准确的玻璃深度。实验表明SILICA在不同未见环境中实现了显著的零样本转移，性能优于现有模型近20%，为透明表面感知设定了新基准。
英文摘要
Standard depth sensors systematically fail on transparent surfaces, creating corrupted 3D maps and severe navigation hazards. While specialized hardware sensors can detect glass, they lack modularity and have extensive hardware dependencies. Consequently, learning-based monocular depth estimation has emerged as a compelling alternative. However, domain-specific glass-aware monocular depth estimators struggle with unfamiliar indoor layouts; restricted by the severe scarcity of real-world glass depth annotations, they fail to generalize zero-shot to new settings. This motivates us to explore whether the extensive priors of text-to-image diffusion models can enable generalizable perception of transparent surfaces. We introduce SILICA, a unified pipeline leveraging these priors to jointly predict glass segmentation and glass-aware depth. This mutual information exchange establishes a robust spatial hierarchy, entirely eliminating the need for paired real-world glass depth annotations. Subsequently, we use the predicted segmentation mask to explicitly filter incorrect glass depth points from standard sensors, recovering accurate metric glass depth for downstream 3D mapping and autonomous collision avoidance. Supported by our novel Mirage 18k dataset, extensive experiments demonstrate that SILICA achieves remarkable zero-shot transfer across diverse, unseen environments, outperforming state-of-the-art models by almost 20% and setting a new benchmark for transparent surface perception.
CommentsIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026
