Shape from Projections via Differentiable Forward Projector

06/29/2020
by   Jakeoung Koo, et al.
0

In tomography, forward projection of 3D meshes has been mostly studied to simulate data acquisition. However, such works did not consider an inverse process of estimating shapes from projections. In this paper, we propose a differentiable forward projector for 3D meshes, to bridge the gap between the forward model for 3D surfaces and optimization. We view the forward projection as a rendering process, and make it differentiable by extending a recent work in differentiable rasterization. We use the proposed forward projector to reconstruct 3D shapes directly from projections. Experimental results for single-object problems show that our method outperforms the traditional voxel-based methods on noisy simulated data. We also apply our method on real data from electron tomography to estimate the shapes of some nanoparticles.

READ FULL TEXT

page 6

page 7

page 8

page 10

research
06/18/2018

RenderNet: A deep convolutional network for differentiable rendering from 3D shapes

Traditional computer graphics rendering pipeline is designed for procedu...
research
11/29/2019

DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing

We propose a differentiable sphere tracing algorithm to bridge the gap b...
research
10/11/2021

Differentiable Stereopsis: Meshes from multiple views using differentiable rendering

We propose Differentiable Stereopsis, a multi-view stereo approach that ...
research
12/08/2020

CoShaRP: A Convex Program for Single-shot Tomographic Shape Sensing

We introduce single-shot X-ray tomography that aims to estimate the targ...
research
03/13/2023

Towards smoother surfaces by applying subdivision to voxel data

In computed tomography, the approximation quality of a scan of a physica...
research
07/30/2021

Shadow Art Revisited: A Differentiable Rendering Based Approach

While recent learning based methods have been observed to be superior fo...
research
01/25/2021

Complexity of Linear Minimization and Projection on Some Sets

The Frank-Wolfe algorithm is a method for constrained optimization that ...

Please sign up or login with your details

Forgot password? Click here to reset