Can I read VIBUS: Data-efficient 3D scene parsing with VIewpoint Bottleneck and Uncertainty-Spectrum modeling on EtoBox?

VIBUS: Data-efficient 3D scene parsing with VIewpoint Bottleneck and Uncertainty-Spectrum modeling by Tian, Beiwen (author);Luo, Liyi (author);Zhao, Hao (author);Zhou, Guyue (author) is a Environmental Science article available to read on EtoBox.

What is VIBUS: Data-efficient 3D scene parsing with VIewpoint Bottleneck and Uncertainty-Spectrum modeling about?

Recently, 3D scenes parsing with deep learning approaches has been a heating topic. However, current methods with fully-supervised models require manually annotated point-wise supervision which is extremely user-unfriendly and time-consuming to obtain. As such, training 3D scene parsing models with sparse supervision is an intriguing alternative. We term this task as data-efficient 3D scene parsing and propose an effective two-stage framework named VIBUS to resolve it by exploiting the enormous unlabeled points. In the first stage, we perform self-supervised representation learning on unlabeled points with the proposed Viewpoint Bottleneck loss function. The loss function is derived from an information bottleneck objective imposed on scenes under different viewpoints, making the process of representation learning free of degradation and sampling. In the second stage, pseudo labels are harvested from the sparse labels based on uncertainty-spectrum modeling. By combining data-driven uncertainty measures and 3D mesh spectrum measures (derived from normal directions and geodesic distances), a robust local affinity metric is obtained. Finite gamma/beta mixture models are used to decompo

Who reads VIBUS: Data-efficient 3D scene parsing with VIewpoint Bottleneck and Uncertainty-Spectrum modeling?

Author

Tian, Beiwen (author);Luo, Liyi (author);Zhao, Hao (author);Zhou, Guyue (author)

Publisher

Elsevier BV

Published

2022

Language

EN

Field

Environmental Science (Physical Sciences)