arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.02759cs.CVcs.AIcs.GRcs.LG
收藏

从稀疏点云进行无监督占据学习

Unsupervised Occupancy Learning from Sparse Point Cloud

Inria(法国国家信息与自动化研究所);Univ. Rennes(雷恩大学);CNRS(法国国家科学研究中心);IRISA(雷恩信息、信号与自动化研究所);M2S(运动、交互与动作实验室)

Amine Ouasfi, Adnane Boukhayma

AI总结:

针对无真值监督下稀疏3D点云形状学习难题,提出推断占据场而非SDF,结合边界不确定性采样、点云监督及熵正则稳定训练,提升隐式形状推断性能。

摘要:

隐式神经表示作为捕捉复杂数据模态的强大框架已受到广泛关注,其涵盖范围从3D形状到图像和音频。在3D形状表示领域,神经符号距离函数(SDF)已展现出忠实地编码复杂形状几何的显著潜力。然而,在缺乏真值监督的情况下从3D点云学习SDF仍然是一项极具挑战性的任务。本文提出一种推断占据场而非SDF的方法,因为占据场更容易从稀疏输入中学习。我们利用基于间隔的不确定性度量,从占据函数的决策边界进行差异化采样,并使用输入点云监督采样的边界点。我们还通过使占据函数偏向最小熵场,同时在输入点云处最大化其熵,来进一步稳定训练早期阶段的优化过程。通过大量实验和评估,我们阐明了所提方法的有效性,突出其在使用合成数据和真实数据时相对于基线方法和最先进方法改进隐式形状推断的能力。

英文摘要:

Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities, encompassing a wide range from 3D shapes to images and audio. Within the realm of 3D shape representation, Neural Signed Distance Functions (SDF) have demonstrated remarkable potential in faithfully encoding intricate shape geometry. However, learning SDFs from 3D point clouds in the absence of ground truth supervision remains a very challenging task. In this paper, we propose a method to infer occupancy fields instead of SDFs as they are easier to learn from sparse inputs. We leverage a margin-based uncertainty measure to differentially sample from the decision boundary of the occupancy function and supervise the sampled boundary points using the input point cloud. We further stabilize the optimization process at the early stages of the training by biasing the occupancy function towards minimal entropy fields while maximizing its entropy at the input point cloud. Through extensive experiments and evaluations, we illustrate the efficacy of our proposed method, highlighting its capacity to improve implicit shape inference with respect to baselines and the state-of-the-art using synthetic and real data.

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。

↑