DeepAI AI Chat
Log In Sign Up

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

by   Kamal Gupta, et al.

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.


page 1

page 7

page 13

page 14

page 15

page 16

page 17

page 18


Render4Completion: Synthesizing Multi-view Depth Maps for 3D Shape Completion

We propose a novel approach for 3D shape completion by synthesizing mult...

3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks

We propose a method for reconstructing 3D shapes from 2D sketches in the...

MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Image

In this paper, we address the problem of reconstructing an object's surf...

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion

This paper introduces MVDiffusion, a simple yet effective multi-view ima...

Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks

We present a novel global representation of 3D shapes, suitable for the ...

Matching with AffNet based rectifications

We consider the problem of two-view matching under significant viewpoint...

BA-Net: Dense Bundle Adjustment Network

This paper introduces a neural network to solve the structure-from-motio...

Code Repositories


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

view repo