ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition

Baslamisli, Anil S.; Das, Partha; Le, Hoang-An; Karaoğlu, Sezer; Gevers, Theo

doi:10.1007/s11263-021-01477-5

Cited by 17 publications

(3 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The topic of multi-illuminant estimation in AWB is capturing a growing interest, with the emergence of appropriately annotated datasets as documented within this paper. The field is currently in its infancy, but we hypothesize a gradual shift toward more methods that produce dense illuminant estimation maps 59 and/or intrinsic decomposition, 60,61 as covered in the past by methods inspired by the Retinex model. 62 One of the main obstacles to multi-illuminant estimation and intrinsic decomposition lies in the collection of appropriatelyannotated datasets.…”

Section: Discussionmentioning

confidence: 99%

Analysis of biases in automatic white balance datasets and methods

Buzzelli

Zini

Bianco

et al. 2022

Color Research & Application

View full text Add to dashboard Cite

Annotated datasets for automatic white balance (AWB) are used for the evaluation and, when necessary, the training, of AWB methods. Relying on such datasets requires awareness of the potential bias in their content and characteristics: some methods are designed to rely on the presence of particular elements, such as human skin, while other methods learn implicit relationships between image content and light properties from training data. The dependency on these relationships makes it fundamental to understand whether the available datasets are actually representative of common application scenarios, such as the presence of human subjects, the diversity of composition, or the illumination conditions. In this paper we overview the most common datasets for Automatic White Balance, including those for single as well as multiple illuminant estimation, providing a critical analysis on their characteristics. Furthermore, we identify a number of existing methods for single illuminant estimation, as a representative pool of approaches to the problem with various levels of complexity. We investigate how the performance of these correlate to the image content of common datasets.

show abstract

Section: Discussionmentioning

confidence: 99%

Analysis of biases in automatic white balance datasets and methods

Buzzelli

Zini

Bianco

et al. 2022

Color Research & Application

View full text Add to dashboard Cite

show abstract

“…Facing the fact that high-quality and denselylabelled intrinsic images are expensive to acquire, many methods have been developed to train models with additional constraints [16,42], reusing physically motivated priors [1,[43][44][45][46], expanding the dataset with synthetic images [15,17,47], or training across datasets [17].…”

Section: Deep Learning Methodsmentioning

confidence: 99%

“…Refs. [45] and [46] derived fine-grained shading components from a physics-based image formation model, in which the shading component is further decomposed into direct and indirect components, and shapedependent/independent ones. These works proposed novel methods by revisiting physically motivated priors.…”

Section: Deep Learning Methodsmentioning

confidence: 99%

Discriminative feature encoding for intrinsic image decomposition

Wang

Liu

2023

Comp. Visual Media

View full text Add to dashboard Cite

Intrinsic image decomposition is an important and long-standing computer vision problem. Given an input image, recovering the physical scene properties is ill-posed. Several physically motivated priors have been used to restrict the solution space of the optimization problem for intrinsic image decomposition. This work takes advantage of deep learning, and shows that it can solve this challenging computer vision problem with high efficiency. The focus lies in the feature encoding phase to extract discriminative features for different intrinsic layers from an input image. To achieve this goal, we explore the distinctive characteristics of different intrinsic components in the high-dimensional feature embedding space. We define feature distribution divergence to efficiently separate the feature vectors of different intrinsic components. The feature distributions are also constrained to fit the real ones through a feature distribution consistency. In addition, a data refinement approach is provided to remove data inconsistency from the Sintel dataset, making it more suitable for intrinsic image decomposition. Our method is also extended to intrinsic video decomposition based on pixel-wise correspondences between adjacent frames. Experimental results indicate that our proposed network structure can outperform the existing state-of-the-art.

show abstract