IPoD：基于点扩散的隐式场学习用于单张RGB-D图像的可泛化三维物体重建
IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images
AI总结：
本文提出IPoD方法，将隐式场学习与点扩散相结合，通过自适应查询点去噪和自条件机制，在单张RGB-D图像的三维物体重建中显著提升了精度与泛化能力。
摘要：
从单视角RGB-D图像进行可泛化的三维物体重建仍然是一项具有挑战性的任务，尤其是在真实世界数据上。当前最先进的方法开发了基于Transformer的隐式场学习，这需要一种密集的学习范式，要求在整个空间中均匀采样密集的查询监督。我们提出了一种新方法IPoD，它将隐式场学习与点扩散相协调。该方法将用于隐式场学习的查询点视为一个带噪声的点云，进行迭代去噪，使其能够动态适应目标物体形状。这种自适应查询点利用了扩散学习在粗略形状恢复方面的能力，同时也增强了隐式表示刻画更精细细节的能力。此外，还设计了一个额外的自条件机制，利用隐式预测作为扩散学习的引导，形成一个协作系统。在CO3D-v2数据集上进行的实验证实了IPoD的优越性，与现有方法相比，F-score提高了7.8%，Chamfer距离改善了28.6%。IPoD的泛化能力也在MVImgNet数据集上得到了验证。我们的项目主页位于https://yushuang-wu.github.io/IPoD。
英文摘要：
Generalizable 3D object reconstruction from single-view RGB-D images remains a challenging task, particularly with real-world data. Current state-of-the-art methods develop Transformer-based implicit field learning, necessitating an intensive learning paradigm that requires dense query-supervision uniformly sampled throughout the entire space. We propose a novel approach, IPoD, which harmonizes implicit field learning with point diffusion. This approach treats the query points for implicit field learning as a noisy point cloud for iterative denoising, allowing for their dynamic adaptation to the target object shape. Such adaptive query points harness diffusion learning's capability for coarse shape recovery and also enhances the implicit representation's ability to delineate finer details. Besides, an additional self-conditioning mechanism is designed to use implicit predictions as the guidance of diffusion learning, leading to a cooperative system. Experiments conducted on the CO3D-v2 dataset affirm the superiority of IPoD, achieving 7.8% improvement in F-score and 28.6% in Chamfer distance over existing methods. The generalizability of IPoD is also demonstrated on the MVImgNet dataset. Our project page is at https://yushuang-wu.github.io/IPoD.
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。
