Fast Light-Weight Near-Field Photometric Stereo

03/30/2022
by   Daniel Lichy, et al.
0

We introduce the first end-to-end learning-based solution to near-field Photometric Stereo (PS), where the light sources are close to the object of interest. This setup is especially useful for reconstructing large immobile objects. Our method is fast, producing a mesh from 52 512×384 resolution images in about 1 second on a commodity GPU, thus potentially unlocking several AR/VR applications. Existing approaches rely on optimization coupled with a far-field PS network operating on pixels or small patches. Using optimization makes these approaches slow and memory intensive (requiring 17GB GPU and 27GB of CPU memory) while using only pixels or patches makes them highly susceptible to noise and calibration errors. To address these issues, we develop a recursive multi-resolution scheme to estimate surface normal and depth maps of the whole image at each step. The predicted depth map at each scale is then used to estimate `per-pixel lighting' for the next scale. This design makes our approach almost 45× faster and 2^∘ more accurate (11.3^∘ vs. 13.3^∘ Mean Angular Error) than the state-of-the-art near-field PS reconstruction technique, which uses iterative optimization.

READ FULL TEXT

page 1

page 6

page 8

page 14

page 16

page 17

page 18

research
09/12/2020

A CNN Based Approach for the Near-Field Photometric Stereo Problem

Reconstructing the 3D shape of an object using several images under diff...
research
04/27/2021

LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo

Three-dimensional reconstruction of objects from shading information is ...
research
10/10/2022

A CNN Based Approach for the Point-Light Photometric Stereo Problem

Reconstructing the 3D shape of an object using several images under diff...
research
07/16/2022

DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Cameras

We propose DiffuStereo, a novel system using only sparse cameras (8 in t...
research
07/11/2022

Edge-preserving Near-light Photometric Stereo with Neural Surfaces

This paper presents a near-light photometric stereo method that faithful...
research
04/11/2022

An Optimal Experimental Design Approach for Light Configurations in Photometric Stereo

This paper presents a technique for finding the surface normal of an obj...
research
08/18/2022

SDA-SNE: Spatial Discontinuity-Aware Surface Normal Estimation via Multi-Directional Dynamic Programming

The state-of-the-art (SoTA) surface normal estimators (SNEs) generally t...

Please sign up or login with your details

Forgot password? Click here to reset