Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors

04/01/2021
by   Jan Bechtold, et al.
0

Single-view 3D object reconstruction has seen much progress, yet methods still struggle generalizing to novel shapes unseen during training. Common approaches predominantly rely on learned global shape priors and, hence, disregard detailed local observations. In this work, we address this issue by learning a hierarchy of priors at different levels of locality from ground truth input depth maps. We argue that exploiting local priors allows our method to efficiently use input observations, thus improving generalization in visible areas of novel shapes. At the same time, the combination of local and global priors enables meaningful hallucination of unobserved parts resulting in consistent 3D shapes. We show that the hierarchical approach generalizes much better than the global approach. It generalizes not only between different instances of a class but also across classes and to unseen arrangements of objects.

READ FULL TEXT

page 5

page 7

page 8

page 12

page 13

page 14

page 15

page 16

research
12/28/2018

Learning to Reconstruct Shapes from Unseen Classes

From a single image, humans are able to perceive the full 3D shape of an...
research
09/13/2018

Learning Shape Priors for Single-View 3D Completion and Reconstruction

The problem of single-view 3D shape completion or reconstruction is chal...
research
04/12/2011

Extracting Parts of 2D Shapes Using Local and Global Interactions Simultaneously

Perception research provides strong evidence in favor of part based repr...
research
01/06/2020

Meshlet Priors for 3D Mesh Reconstruction

Estimating a mesh from an unordered set of sparse, noisy 3D points is a ...
research
08/17/2023

A Fusion of Variational Distribution Priors and Saliency Map Replay for Continual 3D Reconstruction

Single-image 3D reconstruction is a research challenge focused on predic...
research
12/23/2019

Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction

Reconstruction of a 3D shape from a single 2D image is a classical compu...
research
01/12/2017

Surface Reconstruction with Data-driven Exemplar Priors

In this paper, we propose a framework to reconstruct 3D models from raw ...

Please sign up or login with your details

Forgot password? Click here to reset