用扩散模型修复透明与反光物体的深度图，提升3D成像精度。
Diffusion-Based Depth Inpainting for Transparent and Reflective Objects
- 分两阶段：先定位问题区域，再用扩散模型修复深度图。
- 在真实数据集上显著改善透明与反光物体的深度重建效果。
- 适合做3D视觉、机器人感知和增强现实的研究者参考。
透明与反光物体在日常生活中常见，但其独特的视觉和光学特性给三维成像技术带来巨大挑战。传统RGB-D相机难以准确获取这类物体的真实深度值，导致空间信息缺失。为此，我们提出DITR——一种专为透明与反光物体设计的基于扩散模型的深度修复框架。该框架包含两个阶段：区域提议阶段与深度修复阶段，可动态分析光学与几何深度损失，并自动完成修复。大量实验表明，DITR在透明与反光物体的深度修复任务中表现优异，具备强适应性。
原文摘要 · Abstract (English)
Transparent and reflective objects, which are common in our everyday lives, present a significant challenge to 3D imaging techniques due to their unique visual and optical properties. Faced with these types of objects, RGB-D cameras fail to capture the real depth value with their accurate spatial information. To address this issue, we propose DITR, a diffusion-based Depth Inpainting framework specifically designed for Transparent and Reflective objects. This network consists of two stages, including a Region Proposal stage and a Depth Inpainting stage. DITR dynamically analyzes the optical and geometric depth loss and inpaints them automatically. Furthermore, comprehensive experimental results demonstrate that DITR is highly effective in depth inpainting tasks of transparent and reflective objects with robust adaptability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。