SurfNet: Generating 3D shape surfaces using deep residual networks

03/12/2017
by   Ayan Sinha, et al.
0

3D shape models are naturally parameterized using vertices and faces, , composed of polygons forming a surface. However, current 3D learning paradigms for predictive and generative tasks using convolutional neural networks focus on a voxelized representation of the object. Lifting convolution operators from the traditional 2D to 3D results in high computational overhead with little additional benefit as most of the geometry information is contained on the surface boundary. Here we study the problem of directly generating the 3D shape surface of rigid and non-rigid shapes using deep convolutional neural networks. We develop a procedure to create consistent `geometry images' representing the shape surface of a category of 3D objects. We then use this consistent representation for category-specific shape surface generation from a parametric representation or an image by developing novel extensions of deep residual networks for the task of geometry image generation. Our experiments indicate that our network learns a meaningful representation of shape surfaces allowing it to interpolate between shape orientations and poses, invent new shape surfaces and reconstruct 3D shape surfaces from previously unseen images.

READ FULL TEXT

page 4

page 5

page 6

page 7

page 8

research
08/18/2020

Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images

We investigate the problem of learning to generate 3D parametric surface...
research
04/07/2021

Deep Implicit Statistical Shape Models for 3D Medical Image Delineation

3D delineation of anatomical structures is a cardinal goal in medical im...
research
03/29/2022

Target Geometry Estimation Using Deep Neural Networks in Sonar Sensing

Accurate imaging of target shape is a crucial aspect of wideband FM bios...
research
02/04/2021

First-Passage Time Statistics on Surfaces of General Shape: Surface PDE Solvers using Generalized Moving Least Squares (GMLS)

We develop numerical methods for computing statistics of stochastic proc...
research
11/17/2021

DeepCurrents: Learning Implicit Representations of Shapes with Boundaries

Recent techniques have been successful in reconstructing surfaces as lev...
research
12/14/2020

Learning Category-level Shape Saliency via Deep Implicit Surface Networks

This paper is motivated from a fundamental curiosity on what defines a c...
research
06/18/2020

UV-Net: Learning from Curve-Networks and Solids

Parametric curves, surfaces and boundary representations are the basis f...

Please sign up or login with your details

Forgot password? Click here to reset