Learning lightness from human judgement on relative reflectance

Narihira, Takuya; Maire, Michael; Yu, Stella X.

doi:10.1109/cvpr.2015.7298915

Cited by 62 publications

(62 citation statements)

References 23 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intrinsic Images in the Wild (IIW) [5] and Shading Annotations in the Wild (SAW) [6] consist of sparse, crowd-sourced reflectance and shading annotations on real indoor images. Subsequently, several papers train CNN-based classifiers on these sparse annotations and use the classifier outputs as priors to guide decomposition [6,25,26,27]. However, we find these annotations alone are insufficient to train a direct regression approach, likely because they are sparse and are derived from just a few thousand images.…”

Section: Related Workmentioning

confidence: 98%

CGIntrinsics: Better Intrinsic Image Decomposition Through Physically-Based Rendering

Snavely

2018

Lecture Notes in Computer Science

124

184

View full text Add to dashboard Cite

Intrinsic image decomposition is a challenging, long-standing computer vision problem for which ground truth data is very difficult to acquire. We explore the use of synthetic data for training CNN-based intrinsic image decomposition models, then applying these learned models to real-world images. To that end, we present CGINTRINSICS, a new, large-scale dataset of physically-based rendered images of scenes with full ground truth decompositions. The rendering process we use is carefully designed to yield high-quality, realistic images, which we find to be crucial for this problem domain. We also propose a new end-to-end training method that learns better decompositions by leveraging CGINTRINSICS, and optionally IIW and SAW, two recent datasets of sparse annotations on realworld images. Surprisingly, we find that a decomposition network trained solely on our synthetic data outperforms the state-of-the-art on both IIW and SAW, and performance improves even further when IIW and SAW data is added during training. Our work demonstrates the suprising effectiveness of carefully-rendered synthetic data for the intrinsic images task.

show abstract

Section: Related Workmentioning

confidence: 98%

CGIntrinsics: Better Intrinsic Image Decomposition Through Physically-Based Rendering

Snavely

2018

Lecture Notes in Computer Science

124

184

View full text Add to dashboard Cite

show abstract

“…Ordinal relations: There is a long history for learning from ordinal relations, outside the field of computer vision, with particular interest in the area of information retrieval, where many algorithms for learning-to-rank have been developed [7,8,46]. In the context of computer vision, previous works have used relations to learn apparent depth [69,12] or reflectance [29,63] of a scene. We share a common motivation with these approaches in the sense that ordinal relations are easier for humans to annotate, compared to metric depth or absolute reflectance values.…”

Section: Related Workmentioning

confidence: 99%

Ordinal Depth Supervision for 3D Human Pose Estimation

Pavlakos

Zhou

Daniilidis

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

346

240

View full text Add to dashboard Cite

Our ability to train end-to-end systems for 3D human pose estimation from single images is currently constrained by the limited availability of 3D annotations for natural images. Most datasets are captured using Motion Capture (MoCap) systems in a studio setting and it is difficult to reach the variability of 2D human pose datasets, like MPII or LSP. To alleviate the need for accurate 3D ground truth, we propose to use a weaker supervision signal provided by the ordinal depths of human joints. This information can be acquired by human annotators for a wide range of images and poses. We showcase the effectiveness and flexibility of training Convolutional Networks (ConvNets) with these ordinal relations in different settings, always achieving competitive performance with ConvNets trained with accurate 3D joint coordinates. Additionally, to demonstrate the potential of the approach, we augment the popular LSP and MPII datasets with ordinal depth annotations. This extension allows us to present quantitative and qualitative evaluation in non-studio conditions. Simultaneously, these ordinal annotations can be easily incorporated in the training procedure of typical ConvNets for 3D human pose. Through this inclusion we achieve new state-of-the-art performance for the relevant benchmarks and validate the effectiveness of ordinal depth supervision for 3D human pose.

show abstract

“…These indoor scenes are annotated by crowd-sourcing. Although it does not have ground-truth intrinsic images, it is effective in learning priors and relationships in a data-driven manner [28,44,45].…”

Section: Supervised Deep Learningmentioning

confidence: 99%

CNN Based Learning Using Reflection and Retinex Models for Intrinsic Image Decomposition

Baslamisli

Gevers

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Most of the traditional work on intrinsic image decomposition rely on deriving priors about scene characteristics. On the other hand, recent research use deep learning models as in-and-out black box and do not consider the wellestablished, traditional image formation process as the basis of their intrinsic learning process. As a consequence, although current deep learning approaches show superior performance when considering quantitative benchmark results, traditional approaches are still dominant in achieving high qualitative results.In this paper, the aim is to exploit the best of the two worlds. A method is proposed that (1) is empowered by deep learning capabilities, (2) considers a physics-based reflection model to steer the learning process, and (3) exploits the traditional approach to obtain intrinsic images by exploiting reflectance and shading gradient information. The proposed model is fast to compute and allows for the integration of all intrinsic components. To train the new model, an object centered large-scale datasets with intrinsic ground-truth images are created.The evaluation results demonstrate that the new model outperforms existing methods. Visual inspection shows that the image formation loss function augments color reproduction and the use of gradient information produces sharper edges.Datasets, models and higher resolution images are available at https://ivi.fnwi.uva.nl/cv/retinet.

show abstract

Learning lightness from human judgement on relative reflectance

Cited by 62 publications

References 23 publications

CGIntrinsics: Better Intrinsic Image Decomposition Through Physically-Based Rendering

CGIntrinsics: Better Intrinsic Image Decomposition Through Physically-Based Rendering

Ordinal Depth Supervision for 3D Human Pose Estimation

CNN Based Learning Using Reflection and Retinex Models for Intrinsic Image Decomposition

Contact Info

Product

Resources

About