Incorporating Lambertian Priors into Surface Normals Measurement

07/15/2021
by   Yakun Ju, et al.
4

The goal of photometric stereo is to measure the precise surface normal of a 3D object from observations with various shading cues. However, non-Lambertian surfaces influence the measurement accuracy due to irregular shading cues. Despite deep neural networks have been employed to simulate the performance of non-Lambertian surfaces, the error in specularities, shadows, and crinkle regions is hard to be reduced. In order to address this challenge, we here propose a photometric stereo network that incorporates Lambertian priors to better measure the surface normal. In this paper, we use the initial normal under the Lambertian assumption as the prior information to refine the normal measurement, instead of solely applying the observed shading cues to deriving the surface normal. Our method utilizes the Lambertian information to reparameterize the network weights and the powerful fitting ability of deep neural networks to correct these errors caused by general reflectance properties. Our explorations include: the Lambertian priors (1) reduce the learning hypothesis space, making our method learn the mapping in the same surface normal space and improving the accuracy of learning, and (2) provides the differential features learning, improving the surfaces reconstruction of details. Extensive experiments verify the effectiveness of the proposed Lambertian prior photometric stereo network in accurate surface normal measurement, on the challenging benchmark dataset.

READ FULL TEXT

page 1

page 2

page 4

page 7

page 10

page 11

research
12/16/2022

Deep Learning Methods for Calibrated Photometric Stereo and Beyond: A Survey

Photometric stereo recovers the surface normals of an object from multip...
research
12/03/2017

Semi-Global Stereo Matching with Surface Orientation Priors

Semi-Global Matching (SGM) is a widely-used efficient stereo matching te...
research
07/16/2019

Stereo-based terrain traversability analysis using normal-based segmentation and superpixel surface analysis

In this paper, an stereo-based traversability analysis approach for all ...
research
02/28/2018

Neural Photometric Stereo Reconstruction for General Reflectance Surfaces

We present a novel convolutional neural network architecture for photome...
research
03/30/2023

Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation

Most existing approaches for point cloud normal estimation aim to locall...
research
04/21/2021

Improvement of Normal Estimation for PointClouds via Simplifying Surface Fitting

With the burst development of neural networks in recent years, the task ...
research
12/26/2020

Learning Inter- and Intra-frame Representations for Non-Lambertian Photometric Stereo

In this paper, we build a two-stage Convolutional Neural Network (CNN) a...

Please sign up or login with your details

Forgot password? Click here to reset