Improved Modeling of 3D Shapes with Multi-view Depth Maps

09/07/2020 ∙ by Kamal Gupta, et al. ∙ 8

We present a simple yet effective general-purpose framework for modeling 3D shapes by leveraging recent advances in 2D image generation using CNNs. Using just a single depth image of the object, we can output a dense multi-view depth map representation of 3D objects. Our simple encoder-decoder framework, comprised of a novel identity encoder and class-conditional viewpoint generator, generates 3D consistent depth maps. Our experimental results demonstrate the two-fold advantage of our approach. First, we can directly borrow architectures that work well in the 2D image domain to 3D. Second, we can effectively generate high-resolution 3D shapes with low computational memory. Our quantitative evaluations show that our method is superior to existing depth map methods for reconstructing and synthesizing 3D objects and is competitive with other representations, such as point clouds, voxel grids, and implicit functions.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 7

page 13

page 14

page 15

page 16

page 17

page 18

Code Repositories

multiview-shapes

PyTorch implementation of "Improved Modeling of 3D Shapes with Multi-view Depth Maps". 3DV 2020


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.