HYVE:用于神经距离场的混合顶点编码器
HYVE: Hybrid Vertex Encoder for Neural Distance Fields
AI总结:
本文提出HYVE混合顶点编码器,通过多尺度图-体素混合系统与连续可微解码器,在单次前向传播中高效生成有符号或无符号距离场,无需非零距离先验,降低计算开销并提升重建质量。
摘要:
神经形状表示通常指使用神经网络来表示3D几何,例如在特定空间位置计算有符号距离或占用值。本文提出了一种适用于单次前向传播中准确编码3D形状的神经网络架构。我们的架构基于多尺度混合系统,结合了基于图和基于体素的组件,以及一个连续可微的解码器。该混合系统包含一种在神经网络中对基于点的特征进行体素化的新方法,我们证明该方法可与定向点云结合使用,以获得更平滑、更详细的重建结果。此外,我们的网络被训练来求解Eikonal方程,并且仅需知道零水平集即可进行训练和推理。这意味着与大多数先前的形状编码器架构相比,我们的网络能够在没有非零距离值或形状占用显式先验知识的情况下输出有效的有符号距离场。它还仅需单次前向传播,而无需自动解码器方法中使用的潜在代码优化。我们进一步提出对损失函数的修改,以处理表面法线未明确定义的情况,例如非水密表面和非流形几何,从而产生无符号距离场。总体而言,我们的系统有助于减少训练和评估神经距离场的计算开销,并能够应用于困难的几何形状。
英文摘要:
Neural shape representation generally refers to representing 3D geometry using neural networks, e.g., computing a signed distance or occupancy value at a specific spatial position. In this paper we present a neural-network architecture suitable for accurate encoding of 3D shapes in a single forward pass. Our architecture is based on a multi-scale hybrid system incorporating graph-based and voxel-based components, as well as a continuously differentiable decoder. The hybrid system includes a novel way of voxelizing point-based features in neural networks, which we show can be used in combination with oriented point-clouds to obtain smoother and more detailed reconstructions. Furthermore, our network is trained to solve the eikonal equation and only requires knowledge of the zero-level set for training and inference. This means that in contrast to most previous shape encoder architectures, our network is able to output valid signed distance fields without explicit prior knowledge of non-zero distance values or shape occupancy. It also requires only a single forward-pass, instead of the latent-code optimization used in auto-decoder methods. We further propose a modification to the loss function in case that surface normals are not well defined, e.g., in the context of non-watertight surfaces and non-manifold geometry, resulting in an unsigned distance field. Overall, our system can help to reduce the computational overhead of training and evaluating neural distance fields, as well as enabling the application to difficult geometry.
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。