arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.00839cs.CV
收藏

TransNormal: 用于扩散基透明物体法线估计的密集视觉语义

TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation

Zhejiang University(浙江大学);Zhongguancun Academy(中关村学院)

Mingwei Li, Hehe Fan, Yi Yang

AI总结:

TransNormal通过整合密集视觉语义和多任务学习,提升透明物体法线估计的精度与鲁棒性。

摘要:

单目透明物体法线估计对于实验室自动化至关重要,但因其复杂的光线折射和反射而极具挑战性。这些光学特性常常导致传统深度和法线传感器出现灾难性故障,阻碍了在科学环境中的强化人工智能部署。我们提出了TransNormal,一种新的框架,该框架适应了预训练的扩散先验用于单步法线回归。为处理透明表面的纹理缺乏,TransNormal通过交叉注意力机制整合来自DINOv3的密集视觉语义,提供强大的几何提示。此外,我们采用多任务学习目标和基于小波的正则化来确保细粒度结构细节的保留。为了支持此任务,我们引入了TransNormal-Synthetic,一个基于物理的高保真法线图数据集用于透明实验室器皿。广泛的实验表明,TransNormal在ClearGrasp基准上将平均误差减少了24.4%,并提高了11.25°的准确性22.8%;在ClearPose上实现了平均误差减少15.2%。代码和数据集将在https://longxiang-ai.github.io/TransNormal上公开。

英文摘要:

Monocular normal estimation for transparent objects is critical for laboratory automation, yet it remains challenging due to complex light refraction and reflection. These optical properties often lead to catastrophic failures in conventional depth and normal sensors, hindering the deployment of embodied AI in scientific environments. We propose TransNormal, a novel framework that adapts pre-trained diffusion priors for single-step normal regression. To handle the lack of texture in transparent surfaces, TransNormal integrates dense visual semantics from DINOv3 via a cross-attention mechanism, providing strong geometric cues. Furthermore, we employ a multi-task learning objective and wavelet-based regularization to ensure the preservation of fine-grained structural details. To support this task, we introduce TransNormal-Synthetic, a physics-based dataset with high-fidelity normal maps for transparent labware. Extensive experiments demonstrate that TransNormal significantly outperforms state-of-the-art methods: on the ClearGrasp benchmark, it reduces mean error by 24.4% and improves 11.25° accuracy by 22.8%; on ClearPose, it achieves a 15.2% reduction in mean error. The code and dataset will be made publicly available at https://longxiang-ai.github.io/TransNormal.

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。

↑