arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.10403cs.LGcs.AIcs.CVcs.GR
收藏

从分段三线性网络推导多面体复形

Polyhedral Complex Derivation from Piecewise Trilinear Networks

NAVER AI Lab(NAVER人工智能实验室);SNU AIIS(首尔国立大学人工智能与信息研究院)

Jin-Hwa Kim

AI总结:

本文研究分段三线性网络中的网格提取问题,提出解析方法展示eikonal约束下超曲面变为平面,并给出三超曲面交点近似算法,通过实验验证了其正确性与效率。

摘要:

近期深度神经网络可视化的进展为理解其结构以及从连续分段仿射(CPWA)函数中提取网格提供了洞见。与此同时,神经表面表示学习的发展引入了非线性位置编码,以解决诸如谱偏置等问题;然而,这对基于CPWA函数的网格提取技术的应用构成了挑战。本文聚焦于作为位置编码的三线性插值方法,我们提出了理论见解和一种解析网格提取方法,展示了在eikonal约束下,三线性区域内的超曲面如何变换为平面。此外,我们引入了一种近似计算三个超曲面之间交点的方法,从而有助于更广泛的应用。我们通过倒角距离、效率以及角度距离,实证验证了该方法的正确性和简约性,同时考察了eikonal损失与超曲面平面性之间的相关性。

英文摘要:

Recent advancements in visualizing deep neural networks provide insights into their structures and mesh extraction from Continuous Piecewise Affine (CPWA) functions. Meanwhile, developments in neural surface representation learning incorporate non-linear positional encoding, addressing issues like spectral bias; however, this poses challenges in applying mesh extraction techniques based on CPWA functions. Focusing on trilinear interpolating methods as positional encoding, we present theoretical insights and an analytical mesh extraction, showing the transformation of hypersurfaces to flat planes within the trilinear region under the eikonal constraint. Moreover, we introduce a method for approximating intersecting points among three hypersurfaces contributing to broader applications. We empirically validate correctness and parsimony through chamfer distance and efficiency, and angular distance, while examining the correlation between the eikonal loss and the planarity of the hypersurfaces.

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。

↑