TranSplat：用于透明物体操作的表面嵌入引导 3D Gaussian Splatting
TranSplat: Surface Embedding-guided 3D Gaussian Splatting for Transparent Object Manipulation
AI总结：
本文提出 TranSplat，利用潜在扩散模型生成的表面嵌入引导 3D Gaussian Splatting，以提升透明物体的稠密深度补全与机器人抓取性能。
摘要：
透明物体操作在机器人领域仍是一项重大挑战，原因在于难以获取准确且稠密的深度测量。传统深度传感器在面对透明物体时往往失效，导致深度数据不完整或错误。现有深度补全方法难以保证帧间一致性，并且错误地将透明物体建模为 Lambertian 表面，从而造成较差的深度重建效果。为应对这些挑战，我们提出 TranSplat，这是一种专为透明物体定制的、由表面嵌入引导的 3D Gaussian Splatting 方法。TranSplat 使用潜在扩散模型生成表面嵌入，这些嵌入提供一致且连续的表示，使其对视角和光照变化具有鲁棒性。通过将这些表面嵌入与输入 RGB 图像相结合，TranSplat 有效捕捉透明表面的复杂性，增强 3D 高斯的泼溅并改善深度补全。在合成和真实世界透明物体基准以及机器人抓取任务上的评估表明，TranSplat 实现了准确且稠密的深度补全，证明了其在实际应用中的有效性。我们开源了合成数据集和模型：https://github.com/jeongyun0609/TranSplat
英文摘要：
Transparent object manipulation remains a significant challenge in robotics due to the difficulty of acquiring accurate and dense depth measurements. Conventional depth sensors often fail with transparent objects, resulting in incomplete or erroneous depth data. Existing depth completion methods struggle with interframe consistency and incorrectly model transparent objects as Lambertian surfaces, leading to poor depth reconstruction. To address these challenges, we propose TranSplat, a surface embedding-guided 3D Gaussian Splatting method tailored for transparent objects. TranSplat uses a latent diffusion model to generate surface embeddings that provide consistent and continuous representations, making it robust to changes in viewpoint and lighting. By integrating these surface embeddings with input RGB images, TranSplat effectively captures the complexities of transparent surfaces, enhancing the splatting of 3D Gaussians and improving depth completion. Evaluations on synthetic and real-world transparent object benchmarks, as well as robot grasping tasks, show that TranSplat achieves accurate and dense depth completion, demonstrating its effectiveness in practical applications. We open-source synthetic dataset and model: https://github. com/jeongyun0609/TranSplat
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
