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
this https URL

通过结合隐式场学习和点扩散，IPoD 方法在 3D 对象重建方面取得了优越性能，对动态适应目标对象形状以及提高精细细节刻画能力起到了积极作用。在 CO3D-v2 和 MVImgNet 数据集上的实验结果验证了 IPoD 方法在 F 分数和 Chamfer 距离上相对于现有方法的 7.8% 和 28.6% 的改进性能。

IPoD: 使用点扩散进行隐含场学习，从单个 RGB-D 图像进行可推广的三维物体重建

IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D  Object Reconstruction from Single RGB-D Images

Coordinate-based neural implicit representation or implicit fields have been
widely studied for 3D geometry representation or novel view synthesis.
Recently, a series of efforts have been devoted to accelerating the speed and
improving the quality of the coordinate-based implicit field learning. Instead
of learning heavy MLPs to predict the neural implicit values for the query
coordinates, neural voxels or grids combined with shallow MLPs have been
proposed to achieve high-quality implicit field learning with reduced
optimization time. On the other hand, lightweight field representations such as
linear grid have been proposed to further improve the learning speed. In this
paper, we aim for both fast and high-quality implicit field learning, and
propose TaylorGrid, a novel implicit field representation which can be
efficiently computed via direct Taylor expansion optimization on 2D or 3D
grids. As a general representation, TaylorGrid can be adapted to different
implicit fields learning tasks such as SDF learning or NeRF. From extensive
quantitative and qualitative comparisons, TaylorGrid achieves a balance between
the linear grid and neural voxels, showing its superiority in fast and
high-quality implicit field learning.

通过在二维或三维网格上直接进行 Taylor 展开优化，提出了一种名为 TaylorGrid 的新型隐式场表示，旨在实现快速高质量的隐式场学习，并可以适用于 SDF 学习或 NeRF 等不同的隐式场学习任务。通过广泛的定量和定性比较，TaylorGrid 在快速高质量的隐式场学习方面展现出了线性网格和神经体素的优势。