N-SfC: Robust and Fast Shape Estimation from Caustic Images

12/13/2021
by   Marc Kassubeck, et al.
0

This paper deals with the highly challenging problem of reconstructing the shape of a refracting object from a single image of its resulting caustic. Due to the ubiquity of transparent refracting objects in everyday life, reconstruction of their shape entails a multitude of practical applications. The recent Shape from Caustics (SfC) method casts the problem as the inverse of a light propagation simulation for synthesis of the caustic image, that can be solved by a differentiable renderer. However, the inherent complexity of light transport through refracting surfaces currently limits the practicability with respect to reconstruction speed and robustness. To address these issues, we introduce Neural-Shape from Caustics (N-SfC), a learning-based extension that incorporates two components into the reconstruction pipeline: a denoising module, which alleviates the computational cost of the light transport simulation, and an optimization process based on learned gradient descent, which enables better convergence using fewer iterations. Extensive experiments demonstrate the effectiveness of our neural extensions in the scenario of quality control in 3D glass printing, where we significantly outperform the current state-of-the-art in terms of computational speed and final surface error.

READ FULL TEXT

page 3

page 5

page 6

page 7

page 12

page 13

page 14

page 16

research
05/20/2021

Dense Reconstruction of Transparent Objects by Altering Incident Light Paths Through Refraction

This paper addresses the problem of reconstructing the surface shape of ...
research
02/24/2023

3D Surface Reconstruction in the Wild by Deforming Shape Priors from Synthetic Data

Reconstructing the underlying 3D surface of an object from a single imag...
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
06/23/2013

Characterizing Ambiguity in Light Source Invariant Shape from Shading

Shape from shading is a classical inverse problem in computer vision. Th...
research
04/09/2019

Non-Lambertian Surface Shape and Reflectance Reconstruction Using Concentric Multi-Spectral Light Field

Recovering the shape and reflectance of non-Lambertian surfaces remains ...
research
03/03/2022

Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D Reconstruction

Reconstructing 3D objects from 2D images is both challenging for our bra...
research
04/28/2023

3D shape reconstruction of semi-transparent worms

3D shape reconstruction typically requires identifying object features o...

Please sign up or login with your details

Forgot password? Click here to reset