Return
Deep 3D semantic scene extrapolation
DOI:10.1007/s00371-018-1586-7.png)
Abstract
En 中文
Scene extrapolation is a challenging variant of the scene completion problem, which pertains to predicting the missing part(s) of a scene. While the 3D scene completion algorithms in the literature try to fill the occluded part of a scene such as a chair behind a table, we focus on extrapolating the available half-scene information to a full one, a problem that, to our knowledge, has not been studied yet. Our approaches are based on convolutional neural networks (CNN). As input, we take the half of 3D voxelized scenes, then our models complete the other half of scenes as output. Our baseline CNN model consisting of convolutional and ReLU layers with multiple residual connections and Softmax classifier with voxel-wise cross-entropy loss function at the end. We train and evaluate our models on the synthetic 3D SUNCG dataset. We show that our trained networks can predict the other half of the scenes and complete the objects correctly with suitable lengths. With a discussion on the challenges, we propose scene extrapolation as a challenging test bed for future research in deep learning. We made our models available on https://github.com/aliabbasi/d3dsse.
Keywords:
3D scenes
Extrapolation
Convolutional neural networks
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.9
Papers:
4.6K
Citations:
6.5K
Organization
Cited Papers
Subversion of Autophagy in Adherent Invasive Escherichia coli-Infected Neutrophils Induces Inflammation and Cell Death
PLoS ONE
IF0
Molecular Basis of Filamin A-FilGAP Interaction and Its Impairment in Congenital Disorders Associated with Filamin A Mutations
PLoS ONE
IF0

