Intrinsic Image Decomposition with Step and Drift Shading Separation

Bin Sheng, Ping Li, Yuxi Jin, Ping Tan, Tong Yee Lee

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Decomposing an image into the shading and reflectance layers remains challenging due to its severely under-constrained nature. We present an approach based on illumination decomposition that recovers the intrinsic images without additional information, e.g., depth or user interaction. Our approach is based on the rationale that the shading component contains the step and drift channels simultaneously. We decompose the illumination into two channels: the step shading, corresponding to the sharp shading changes due to cast shadow or abrupt shape changes; the drift shading, accounting for the smooth shading variations due to gradual illumination changes or slow shape changes. Due to such transformation of turning the conventional assumption that shading has smoothness as reasonable prior, our model has the advantages in handling real images, especially with the cast shadows or strong shape edges. We also apply a much stricter edge classifier along with a reinforcement process to enhance our method. We formulate the problem using a two-parameter energy function and split it into two energy functions corresponding to the reflectance and step shading. Experiments on the MIT dataset, the IIW dataset and the MPI Sintel dataset have shown the success of our approach over the state-of-the-art methods.

Original languageEnglish
Article number8457312
Pages (from-to)1332-1346
Number of pages15
JournalIEEE Transactions on Visualization and Computer Graphics
Volume26
Issue number2
DOIs
Publication statusPublished - 2020 Feb 1

Fingerprint

Lighting
Decomposition
Reinforcement
Classifiers
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Cite this

Sheng, Bin ; Li, Ping ; Jin, Yuxi ; Tan, Ping ; Lee, Tong Yee. / Intrinsic Image Decomposition with Step and Drift Shading Separation. In: IEEE Transactions on Visualization and Computer Graphics. 2020 ; Vol. 26, No. 2. pp. 1332-1346.
@article{f2c3ba88fa374c869e3556a4bf0b7b71,
title = "Intrinsic Image Decomposition with Step and Drift Shading Separation",
abstract = "Decomposing an image into the shading and reflectance layers remains challenging due to its severely under-constrained nature. We present an approach based on illumination decomposition that recovers the intrinsic images without additional information, e.g., depth or user interaction. Our approach is based on the rationale that the shading component contains the step and drift channels simultaneously. We decompose the illumination into two channels: the step shading, corresponding to the sharp shading changes due to cast shadow or abrupt shape changes; the drift shading, accounting for the smooth shading variations due to gradual illumination changes or slow shape changes. Due to such transformation of turning the conventional assumption that shading has smoothness as reasonable prior, our model has the advantages in handling real images, especially with the cast shadows or strong shape edges. We also apply a much stricter edge classifier along with a reinforcement process to enhance our method. We formulate the problem using a two-parameter energy function and split it into two energy functions corresponding to the reflectance and step shading. Experiments on the MIT dataset, the IIW dataset and the MPI Sintel dataset have shown the success of our approach over the state-of-the-art methods.",
author = "Bin Sheng and Ping Li and Yuxi Jin and Ping Tan and Lee, {Tong Yee}",
year = "2020",
month = "2",
day = "1",
doi = "10.1109/TVCG.2018.2869326",
language = "English",
volume = "26",
pages = "1332--1346",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "2",

}

Intrinsic Image Decomposition with Step and Drift Shading Separation. / Sheng, Bin; Li, Ping; Jin, Yuxi; Tan, Ping; Lee, Tong Yee.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 26, No. 2, 8457312, 01.02.2020, p. 1332-1346.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Intrinsic Image Decomposition with Step and Drift Shading Separation

AU - Sheng, Bin

AU - Li, Ping

AU - Jin, Yuxi

AU - Tan, Ping

AU - Lee, Tong Yee

PY - 2020/2/1

Y1 - 2020/2/1

N2 - Decomposing an image into the shading and reflectance layers remains challenging due to its severely under-constrained nature. We present an approach based on illumination decomposition that recovers the intrinsic images without additional information, e.g., depth or user interaction. Our approach is based on the rationale that the shading component contains the step and drift channels simultaneously. We decompose the illumination into two channels: the step shading, corresponding to the sharp shading changes due to cast shadow or abrupt shape changes; the drift shading, accounting for the smooth shading variations due to gradual illumination changes or slow shape changes. Due to such transformation of turning the conventional assumption that shading has smoothness as reasonable prior, our model has the advantages in handling real images, especially with the cast shadows or strong shape edges. We also apply a much stricter edge classifier along with a reinforcement process to enhance our method. We formulate the problem using a two-parameter energy function and split it into two energy functions corresponding to the reflectance and step shading. Experiments on the MIT dataset, the IIW dataset and the MPI Sintel dataset have shown the success of our approach over the state-of-the-art methods.

AB - Decomposing an image into the shading and reflectance layers remains challenging due to its severely under-constrained nature. We present an approach based on illumination decomposition that recovers the intrinsic images without additional information, e.g., depth or user interaction. Our approach is based on the rationale that the shading component contains the step and drift channels simultaneously. We decompose the illumination into two channels: the step shading, corresponding to the sharp shading changes due to cast shadow or abrupt shape changes; the drift shading, accounting for the smooth shading variations due to gradual illumination changes or slow shape changes. Due to such transformation of turning the conventional assumption that shading has smoothness as reasonable prior, our model has the advantages in handling real images, especially with the cast shadows or strong shape edges. We also apply a much stricter edge classifier along with a reinforcement process to enhance our method. We formulate the problem using a two-parameter energy function and split it into two energy functions corresponding to the reflectance and step shading. Experiments on the MIT dataset, the IIW dataset and the MPI Sintel dataset have shown the success of our approach over the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85053141251&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053141251&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2018.2869326

DO - 10.1109/TVCG.2018.2869326

M3 - Article

AN - SCOPUS:85053141251

VL - 26

SP - 1332

EP - 1346

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 2

M1 - 8457312

ER -