Shape estimation using polarization and shading from two views

GA Atkinson, ER Hancock - IEEE transactions on pattern …, 2007 - ieeexplore.ieee.org
This paper presents a novel method for 3D surface reconstruction that uses polarization and
shading information from two views. The method relies on the polarization data acquired …

Shape and albedo from multiple images using integrability

A Yuille, D Snow - … of IEEE Computer Society Conference on …, 1997 - ieeexplore.ieee.org
Previous work has developed an approach for estimating shape and albedo from multiple
images assuming Lambertian reflectance with single light sources. The main contributions of …

Appearance characterization of linear lambertian objects, generalized photometric stereo, and illumination-invariant face recognition

SK Zhou, G Aggarwal, R Chellappa… - IEEE Transactions on …, 2007 - ieeexplore.ieee.org
Traditional photometric stereo algorithms employ a Lambertian reflectance model with a
varying albedo field and involve the appearance of only one object. In this paper, we …

Cross-modal deep face normals with deactivable skip connections

VF Abrevaya, A Boukhayma… - Proceedings of the …, 2020 - openaccess.thecvf.com
We present an approach for estimating surface normals from in-the-wild color images of
faces. While data-driven strategies have been proposed for single face images, limited …

Attached shadow coding: Estimating surface normals from shadows under unknown reflectance and lighting conditions

T Okabe, I Sato, Y Sato - 2009 IEEE 12th International …, 2009 - ieeexplore.ieee.org
We present a novel technique, termed attached shadow coding, for estimating surface
normals from shadows when the reflectance and lighting conditions are unknown. Our key …

A new perspective on uncalibrated photometric stereo

T Papadhimitri, P Favaro - … of the IEEE Conference on Computer …, 2013 - cv-foundation.org
We investigate the problem of reconstructing normals, albedo and lights of Lambertian
surfaces in uncalibrated photometric stereo under the perspective projection model. Our …

Video compression with adaptive view-dependent lighting removal

D Pang, C Pitts, K Akeley - US Patent 10,567,464, 2020 - Google Patents
US10567464B2 - Video compression with adaptive view-dependent lighting removal -
Google Patents US10567464B2 - Video compression with adaptive view-dependent …

Masked fake face detection using radiance measurements

Y Kim, J Na, S Yoon, J Yi - JOSA A, 2009 - opg.optica.org
This research presents a novel 2D feature space where real faces and masked fake faces
can be effectively discriminated. We exploit the reflectance disparity based on albedo …

[HTML][HTML] Perceptual biases in the interpretation of 3D shape from shading

B Liu, JT Todd - Vision research, 2004 - Elsevier
Two experiments are reported in which observers judged the sign and magnitude of surface
curvature from shaded images of an indoor scene. The depicted surfaces were illuminated …

Compensating for sensor saturation and microlens modulation during light-field image processing

KB Akeley, B Cabral, C Pitts, CK Liang… - US Patent …, 2015 - Google Patents
(60) Provisional application No. 61/604,155, filed on Feb. According to various
embodiments, the system and method 28, 2012, provisional application No. 61/604,175, of …