A Comprehensive Multi-Illuminant Dataset for Benchmarking of the Intrinsic Image Algorithms

Beigpour, Shida; Kolb, Andreas; Kunz, Sven

doi:10.1109/iccv.2015.28

Cited by 10 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This dataset has led to important progress in intrinsic image decomposition, but the small size of the dataset, and its focus on single objects rather than entire scenes, means that it is not well suited to machine learning approaches on natural images. Beigpour et al capture a dataset of similar size, but with multiple illuminants [3]. Bell et al released the Intrinsic Images in the Wild (IIW) dataset [5], a large-scale dataset with over 5K real-world indoor photos, with relative reflectance judgments between millions of pairs of points.…”

Section: Related Workmentioning

confidence: 99%

Shading Annotations in the Wild

Kovács

Bell

Snavely

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Understanding shading effects in images is critical for a variety of vision and graphics problems, including intrinsic image decomposition, shadow removal, image relighting, and inverse rendering. As is the case with other vision tasks, machine learning is a promising approach to understanding shading-but there is little ground truth shading data available for real-world images. We introduce Shading Annotations in the Wild (SAW), a new large-scale, public dataset of shading annotations in indoor scenes, comprised of multiple forms of shading judgments obtained via crowdsourcing, along with shading annotations automatically generated from RGB-D imagery. We use this data to train a convolutional neural network to predict per-pixel shading information in an image. We demonstrate the value of our data and network in an application to intrinsic images, where we can reduce decomposition artifacts produced by existing algorithms. Our database is available at

show abstract

Section: Related Workmentioning

confidence: 99%

Shading Annotations in the Wild

Kovács

Bell

Snavely

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…Also, the rankings are only about albedo, hence this dataset is insu cient for full IID. In the Multi-illuminant Intrinsic Image Dataset [14] real photos of 5 distinct scenes are captured under complex multi-illuminant and multi-colored illumination conditions, while shadows are also included in the scenes. This dataset consists of challenging scenes with ground truths for reflectance, shading, specularity, illumination and preliminary depth information, yet it has shortcomings.…”

Section: Introductionmentioning

confidence: 99%

IID-NORD: A Comprehensive Intrinsic Image Decomposition Dataset

Karakaya

Ulucan

Ebner

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

The goal of intrinsic image decomposition is to recover low level features of images. Most of the studies tend to consider only reflectance and shading, even though it is known that increasing the number of intrinsics is beneficial for many applications. Existing intrinsic image datasets are quite limited. In this study, a dataset is introduced to provide a comprehensive benchmark to the field of intrinsic image decomposition. IID-NORD contains a large number of scenes and for each scene ground truth reflectance, shading, surface normal vectors, light vectors and depth map is provided to allow detailed decomposition. Moreover, diverse illuminants, viewing angles, and dynamic shadows are used to prevent any bias. To the best of available knowledge, IID-NORD is the most comprehensive dataset in the field of intrinsic image decomposition. IID-NORD will be available on the first author's o cial webpage.

show abstract

“…It has served this purpose well, but lacks realism and diversity. Recently, [4] proposed an extension to multi illuminants, but without overcoming the limitations on extent. Another possible route to generate datasets is the use of computer graphics rendering engines.…”

Section: Introductionmentioning

confidence: 99%

Reflectance Adaptive Filtering Improves Intrinsic Image Estimation

Nestmeyer

Gehler

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Separating an image into reflectance and shading layers poses a challenge for learning approaches because no large corpus of precise and realistic ground truth decompositions exists. The Intrinsic Images in the Wild (IIW) dataset provides a sparse set of relative human reflectance judgments, which serves as a standard benchmark for intrinsic images. A number of methods use IIW to learn statistical dependencies between the images and their reflectance layer. Although learning plays an important role for high performance, we show that a standard signal processing technique achieves performance on par with current state-of-the-art. We propose a loss function for CNN learning of dense reflectance predictions. Our results show a simple pixel-wise decision, without any context or prior knowledge, is sufficient to provide a strong baseline on IIW. This sets a competitive baseline which only two other approaches surpass. We then develop a joint bilateral filtering method that implements strong prior knowledge about reflectance constancy. This filtering operation can be applied to any intrinsic image algorithm and we improve several previous results achieving a new state-of-the-art on IIW. Our findings suggest that the effect of learning-based approaches may have been over-estimated so far. Explicit prior knowledge is still at least as important to obtain high performance in intrinsic image decompositions.

show abstract

A Comprehensive Multi-Illuminant Dataset for Benchmarking of the Intrinsic Image Algorithms

Cited by 10 publications

References 27 publications

Shading Annotations in the Wild

Shading Annotations in the Wild

IID-NORD: A Comprehensive Intrinsic Image Decomposition Dataset

Reflectance Adaptive Filtering Improves Intrinsic Image Estimation

Contact Info

Product

Resources

About