RECORD
STAR: A Structure and Texture Aware Retinex Model
Computer Vision and Pattern Recognition · Submitted 16 Jun 2019
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Comprehensive experiments on commonly tested datasets demonstrate that, the proposed STAR model produce better quantitative and qualitative performance than previous competing methods, on illumination and reflectance decomposition, low-light image enhancement, and color correction.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Retinex theory is developed mainly to decompose an image into the illumination and reflectance components by analyzing local image derivatives. In this theory, larger derivatives are attributed to the changes in reflectance, while smaller derivatives are emerged in the smooth illumination. In this paper, we utilize exponentiated local derivatives (with an exponent {\gamma}) of an observed image to generate its structure map and texture map. The structure map is produced by been amplified with {\gamma} > 1, while the texture map is generated by been shrank with {\gamma} < 1. To this end, we design exponential filters for the local derivatives, and present their capability on extracting accurate structure and texture maps, influenced by the choices of exponents {\gamma}. The extracted structure and texture maps are employed to regularize the illumination and reflectance components in Retinex decomposition. A novel Structure and Texture Aware Retinex (STAR) model is further proposed for illumination and reflectance decomposition of a single image. We solve the STAR model by an alternating optimization algorithm. Each sub-problem is transformed into a vectorized least squares regression, with closed-form solutions. Comprehensive experiments on commonly tested datasets demonstrate that, the proposed STAR model produce better quantitative and qualitative performance than previous competing methods, on illumination and reflectance decomposition, low-light image enhancement, and color correction. The code is publicly available at https://github.com/csjunxu/STAR.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Retinex theory is developed mainly to decompose an image into the illumination and reflectance components by analyzing local image derivatives. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | In this theory, larger derivatives are attributed to the changes in reflectance, while smaller derivatives are emerged in the smooth illumination. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s2 | In this paper, we utilize exponentiated local derivatives (with an exponent {\gamma}) of an observed image to generate its structure map and texture map. | method 0.86 | 0.93 | 0.03 | asserted 0.99 |
| s3 | The structure map is produced by been amplified with {\gamma} > 1, while the texture map is generated by been shrank with {\gamma} < 1. | method 0.98 | 0.84 | 0.04 | asserted 1.00 |
| s4 | To this end, we design exponential filters for the local derivatives, and present their capability on extracting accurate structure and texture maps, influenced by the choices of exponents {\gamma}. | method 0.79 | 0.91 | 0.04 | asserted 0.97 |
| s5 | The extracted structure and texture maps are employed to regularize the illumination and reflectance components in Retinex decomposition. | method 0.96 | 0.81 | 0.04 | asserted 0.99 |
| s6 | A novel Structure and Texture Aware Retinex (STAR) model is further proposed for illumination and reflectance decomposition of a single image. | contribution 0.94 | 0.91 | 0.14 | asserted 1.00 |
| s7 | We solve the STAR model by an alternating optimization algorithm. | method 0.99 | 0.93 | 0.02 | asserted 1.00 |
| s8 | Each sub-problem is transformed into a vectorized least squares regression, with closed-form solutions. | method 1.00 | 0.90 | 0.02 | asserted 1.00 |
| s9 | Comprehensive experiments on commonly tested datasets demonstrate that, the proposed STAR model produce better quantitative and qualitative performance than previous competing methods, on illumination and reflectance decomposition, low-light image enhancement, and color correction. | result 1.00 | 0.95 | 0.87 | asserted 1.00 |
| s10 | The code is publicly available at https://github.com/csjunxu/STAR. | contribution 0.72 | 0.45 | 0.02 | asserted 0.98 |
What was examined, and what was not
- arXiv listing abstract v5
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Retinex theory is developed mainly to decompose an image into the illumination and reflectance components by analyzing local image derivatives. In this theory, larger derivatives are attributed to the changes in reflectance, while smaller derivatives are emerged in the smooth illumination. In this paper, we utilize exponentiated local derivatives (with an exponent {\gamma}) of an observed image to generate its structure map and texture map. The structure map is produced by been amplified with {\gamma} > 1, while the texture map is generated by been shrank with {\gamma} < 1. To this end, we design exponential filters for the local derivatives, and present their capability on extracting accurate structure and texture maps, influenced by the choices of exponents {\gamma}. The extracted structure and texture maps are employed to regularize the illumination and reflectance components in Retinex decomposition. A novel Structure and Texture Aware Retinex (STAR) model is further proposed for illumination and reflectance decomposition of a single image. We solve the STAR model by an alternating optimization algorithm. Each sub-problem is transformed into a vectorized least squares regression, with closed-form solutions. Comprehensive experiments on commonly tested datasets demonstrate that, the proposed STAR model produce better quantitative and qualitative performance than previous competing methods, on illumination and reflectance decomposition, low-light image enhancement, and color correction. The code is publicly available at https://github.com/csjunxu/STAR.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 1 sentence without a confident label
Cites as background 2 papers
-
Besides, the Retinex decomposition methods can be applied into low-light image enhancement [ref] and color correction [ref] .
A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement · Retinex Model · 0.85
-
Besides, the Retinex decomposition methods can be applied into low-light image enhancement [ref] and color correction [ref] .
Color Constancy by GANs: An Experimental Survey · Retinex Model · 0.85
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.