Reconstructing 3D geometry from \emph{unoriented} point clouds can benefit many downstream tasks. Recent shape modeling methods mostly adopt implicit neural representation to fit a signed distance field (SDF) and optimize the network by \emph{unsigned} supervision. However, these methods occasionally have difficulty in finding the coarse shape for complicated objects, especially suffering from the ``ghost'' surfaces (\ie, fake surfaces that should not exist). To guide the network quickly fit the coarse shape, we propose to utilize the signed supervision in regions that are obviously outside the object and can be easily determined, resulting in our semi-signed supervision. To better recover high-fidelity details, a novel importance sampling based on tracked region losses and a progressive positional encoding (PE) prioritize the optimization towards underfitting and complicated regions. Specifically, we voxelize and partition the object space into \emph{sign-known} and \emph{sign-uncertain} regions, in which different supervisions are applied. Besides, we adaptively adjust the sampling rate of each voxel according to the tracked reconstruction loss, so that the network can focus more on the complicated under-fitting regions. To this end, we propose our semi-signed prioritized (SSP) neural fitting, and conduct extensive experiments to demonstrate that SSP achieves state-of-the-art performance on multiple datasets including the ABC subset and various challenging data. The code will be released upon the publication.
翻译:从 emph{unmitr} 点云重建 3D 几何方法可以帮助许多下游任务 。 最近的形状模型方法大多采用隐含神经表示法, 以适合签名的距离场( SDF), 并通过\ emph{unmitr} 监督优化网络。 但是, 这些方法有时难以找到复杂物体的粗糙形状, 特别是受“ ghost” 表面(\, 假表面, 不应该存在 ) 影响。 为了快速引导网络适合粗糙的形状, 我们提议在明显不在目标范围、可以轻易确定、导致我们半签名监督的区域使用已签名的监督。 要更好地恢复高纤维度的细节, 以跟踪区域损失为基础的新型重要取样, 以及渐进式定位编码( PE) 将优化到不完善和复杂的区域 。 具体地说, 我们将物体空间的蒸馏和分区分隔成, 将应用不同的监视系统。 此外, 我们调整了每个oxel 的取样率率, 包括跟踪的重建过程, SSP 将显示我们最复杂的数据 的运行过程 。