Efficient and Robust Inverse Lighting of a Single Face Image Using Compressive Sensing

Conde, Miguel Heredia; Shahlaei, Davoud; Blanz, Volker; Loffeld, Otmar

doi:10.1109/iccvw.2015.38

Cited by 5 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Blanz and Vetter [9] proposed to estimate the ambient and directional light as a byproduct of fitting 3D Morphable Models (3DMM) to a single face image. Since then, several 3DMM based methods were proposed [2,25,17,30,33]. The performance of these methods rely on a good 3DMM of faces.…”

Section: Related Workmentioning

confidence: 99%

“…There exist many approaches for lighting estimation from a single face image [6,30,17,25], however they are not learning-based and rely on complicated optimization during testing, making the process inefficient. Moreover, the performance of these methods (e.g., [6]) depends on the resolution of face images, and cannot give accurate predictions for low resolution images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces

Zhou

Sun

Yacoob

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Lighting estimation from face images is an important task and has applications in many areas such as image editing, intrinsic image decomposition, and image forgery detection. We propose to train a deep Convolutional Neural Network (CNN) to regress lighting parameters from a single face image. Lacking massive ground truth lighting labels for face images in the wild, we use an existing method to estimate lighting parameters, which are treated as ground truth with unknown noises. To alleviate the effect of such noises, we utilize the idea of Generative Adversarial Networks (GAN) and propose a Label Denoising Adversarial Network (LDAN) to make use of synthetic data with accurate ground truth to help train a deep CNN for lighting regression on real face images. Experiments show that our network outperforms existing methods in producing consistent lighting parameters of different faces under similar lighting conditions. Moreover, our method is 100,000 times faster in execution time than prior optimization-based lighting estimation approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces

Zhou

Sun

Yacoob

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Meanwhile, various methods are proposed to tackle illumination changes on human faces. The state-of-theart methods of face inverse lighting [7,40] usually fit the face region to a 3D Morphable Model [29] by facial landmarks and then render illumination. However, these methods are unsuitable to face thumbnails, because facial landmark cannot be detected accurately in such lowresolution images and erroneous face alignment leads to artifacts in the illumination normalized results.…”

Section: Introductionmentioning

confidence: 99%

Copy and Paste GAN: Face Hallucination from Shaded Thumbnails

Zhang¹,

Tsang

Luo

et al. 2020

Preprint

View full text Add to dashboard Cite

Existing face hallucination methods based on convolutional neural networks (CNN) have achieved impressive performance on low-resolution (LR) faces in a normal illumination condition. However, their performance degrades dramatically when LR faces are captured in low or non-uniform illumination conditions. This paper proposes a Copy and Paste Generative Adversarial Network (CPGAN) to recover authentic high-resolution (HR) face images while compensating for low and nonuniform illumination. To this end, we develop two key components in our CPGAN: internal and external Copy and Paste nets (CPnets). Specifically, our internal CPnet exploits facial information residing in the input image to enhance facial details; while our external CPnet leverages an external HR face for illumination compensation. A new illumination compensation loss is thus developed to capture illumination from the external guided face image effectively. Furthermore, our method offsets illumination and upsamples facial details alternately in a coarse-to-fine fashion, thus alleviating the correspondence ambiguity between LR inputs and external HR inputs. Extensive experiments demonstrate that our method manifests authentic HR face images in a uniform illumination condition and outperforms state-of-the-art methods qualitatively and quantitatively.

show abstract

Robust approach to inverse lighting using RGB-D images

Choe

Shim

2018

Information Sciences

View full text Add to dashboard Cite

Efficient and Robust Inverse Lighting of a Single Face Image Using Compressive Sensing

Cited by 5 publications

References 30 publications

Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces

Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces

Copy and Paste GAN: Face Hallucination from Shaded Thumbnails

Robust approach to inverse lighting using RGB-D images

Contact Info

Product

Resources

About