Geometry-Aware Face Completion and Editing

Face completion is a challenging generation task because it requires generating visually pleasing new pixels that are semantically consistent with the unmasked face region. This paper proposes a geometry-aware Face Completion and Editing NETwork (FCENet) by systematically studying facial geometry from the unmasked region. Firstly, a facial geometry estimator is learned to estimate facial landmark heatmaps and parsing maps from the unmasked face image. Then, an encoder-decoder structure generator serves to complete a face image and disentangle its mask areas conditioned on both the masked face image and the estimated facial geometry images. Besides, since low-rank property exists in manually labeled masks, a low-rank regularization term is imposed on the disentangled masks, enforcing our completion network to manage occlusion area with various shape and size. Furthermore, our network can generate diverse results from the same masked input by modifying estimated facial geometry, which provides a flexible mean to edit the completed face appearance. Extensive experimental results qualitatively and quantitatively demonstrate that our network is able to generate visually pleasing face completion results and edit face attributes as well.

Talking Face Generation by Adversarially Disentangled Audio-Visual Representation

Talking face generation aims to synthesize a sequence of face images that correspond to a clip of speech. This is a challenging task because face appearance variation and semantics of speech are coupled together in the subtle movements of the talking face regions. Existing works either construct specific face appearance model on specific subjects or model the transformation between lip motion and speech. In this work, we integrate both aspects and enable arbitrary-subject talking face generation by learning disentangled audio-visual representation. We find that the talking face sequence is actually a composition of both subject-related information and speech-related information. These two spaces are then explicitly disentangled through a novel associative-and-adversarial training process. This disentangled representation has an advantage where both audio and video can serve as inputs for generation. Extensive experiments show that the proposed approach generates realistic talking face sequences on arbitrary subjects with much clearer lip motion patterns than previous work. We also demonstrate the learned audio-visual representation is extremely useful for the tasks of automatic lip reading and audio-video retrieval.

A THIRTY-ONE-YEARS-OLD FEMALE WITH SLE AND SYSTEMIC SCLERODERMA (Perempuan Usia 31 Tahun dengan SLE dan Skleroderma Sistemik)

Systemic Lupus Erythematosus (SLE) adalah penyakit rematik autoimun yang ditandai adanya inflamasi luas, yang mempengaruhisetiap organ atau sistem dalam tubuh. Sklerosis sistemik (skleroderma) adalah penyakit multisistem kronis yang tidak diketahuipenyebabnya, ditandai dengan penebalan kulit akibat penumpukan jaringan ikat disertai kelainan fungsi dan bentuk organ visceral.Seorang perempuan 31 tahun mengalami nyeri jari-jari dan sendi. Lima tahun lalu didiagnosis kusta serta diobati selama satu tahun.Pemeriksaan fisik didapatkan mouse face appearance, teleangiektasis, salt and pepper appearance, sclerodactili, artritis, serta calcinosis.Peregangan dan pengerasan kulit simetris. Hemoglobin menurun, sediaan darah tepi terdapat sebaran roleaux, neutrofilia dan limfositteraktivasi. Indirect Coomb Test (ICT) inkompatibel. SGOT, total protein, globulin meningkat. Anti Ds-DNA meningkat lima kali dan ANAmeningkat dua puluh kali lipat dari batas normal. Diagnosis SLE didasarkan pada peningkatan kadar ANA dan Ds-DNA. Sklerodermadidasarkan pada pemeriksaan fisik, pemeriksaan hematologi dan anti Scl-70 (anti tropoisomerase I)

Illumination Invariant Face Recognition

Illumination variation is one of the well-known problems in face recognition, especially in uncontrolled environments. This chapter presents an extensive and up-to-date survey of the existing techniques to address this problem. This survey covers the conventional passive techniques that attempt to solve the illumination problem by studying the visible light images, in which face appearance has been altered by varying illumination, as well as the active techniques that aim to obtain images of face modalities invariant to environmental illumination.