Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data

Lyu, Junfeng; Wang, Zhen; Xu, Feng

doi:10.1109/cvpr52688.2022.00342

Cited by 9 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several face swapping algorithms are based on the 3D face model [20,24]. Face2Face [31] transferred expres- sions from source to target face by fitting a 3D morphable face model (3DMM) [30].…”

Section: D Face Methodsmentioning

confidence: 99%

End-to-end Face-swapping via Adaptive Latent Representation Learning

Lin¹,

Hu²,

Shen³

et al. 2023

Preprint

View full text Add to dashboard Cite

Section: D Face Methodsmentioning

confidence: 99%

End-to-end Face-swapping via Adaptive Latent Representation Learning

Lin¹,

Hu²,

Shen³

et al. 2023

Preprint

View full text Add to dashboard Cite

“…The first stage is glass removal, where we remove both the reading glass and the cast shadow from the face image. We employ two networks, Shadow Mask Network and Glass Mask Network [58], for the glass removal. Given an input image I real , we generate two masks: a glass mask M g real using the glass mask network and a shadow mask M s real using the shadow mask network.…”

Section: ) Face Caricature Dataset With Occulsionmentioning

confidence: 99%

“…Given an input image I real , we generate two masks: a glass mask M g real using the glass mask network and a shadow mask M s real using the shadow mask network. We use item removal from [58] to remove both the eyeglass and the shadow from the face image and generate a new face image I ng real with no eyeglass and cast shadow.…”

Section: ) Face Caricature Dataset With Occulsionmentioning

confidence: 99%

High-Quality Face Caricature via Style Translation

Laishram,

Shaheryar,

Lee

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Caricature is an exaggerated form of artistic portraiture that accentuates unique yet subtle characteristics of human faces. Recently, advancements in deep end-to-end techniques have yielded encouraging outcomes in capturing both style and elevated exaggerations in creating face caricatures. The majority of these approaches tend to produce cartoon-like results that are impractical for real-world applications. In this study, we proposed a high-quality, unpaired face caricature method that is appropriate for use in the real world and uses computer vision techniques and GAN models. We attain the exaggeration of facial features and the stylization of appearance through a two-step process: Face caricature generation and face caricature projection. The face caricature generation step creates new caricature face datasets from real images and trains a generative model using the real and newly created caricature datasets. The Face caricature projection employs an encoder, which is trained with real and caricature faces with the pretrained generator to project real and caricature faces. Using the encoder and generator's latent space, we perform an iterative facial exaggeration from the real image to the caricature faces. Our projection preserves the facial identity, attributes, and expressions from the input image. Also, it accounts for facial occlusions, such as reading glasses or sunglasses, to enhance the robustness of our model. Furthermore, we conducted a comprehensive comparison of our approach with various state-of-the-art face caricature methods, which highlighted the distinctiveness and exceptional realism of our process.

show abstract