Deep Cascaded Bi-Network for Face Hallucination

We present a novel framework for hallucinating faces of unconstrained poses and with very low resolution (face size as small as 5pxIOD). In contrast to existing studies that mostly ignore or assume pre-aligned face spatial configuration (e.g. facial landm

  • PDF / 4,573,480 Bytes
  • 17 Pages / 439.37 x 666.142 pts Page_size
  • 57 Downloads / 216 Views

DOWNLOAD

REPORT


Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong, China {zs014,ccloy,xtang}@ie.cuhk.edu.hk, [email protected] 2 University of California, Merced, Merced, USA 3 Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

Abstract. We present a novel framework for hallucinating faces of unconstrained poses and with very low resolution (face size as small as 5pxIOD). In contrast to existing studies that mostly ignore or assume pre-aligned face spatial configuration (e.g. facial landmarks localization or dense correspondence field), we alternatingly optimize two complementary tasks, namely face hallucination and dense correspondence field estimation, in a unified framework. In addition, we propose a new gated deep bi-network that contains two functionality-specialized branches to recover different levels of texture details. Extensive experiments demonstrate that such formulation allows exceptional hallucination quality on in-the-wild low-res faces with significant pose and illumination variations.

1

Introduction

Increasing attention is devoted to detection of small faces with an image resolution as low as 10 pixels of height [1]. Meanwhile, facial analysis techniques, such as face alignment [2,3] and verification [4,5], have seen rapid progress. However, the performance of most existing techniques would degrade when given a low resolution facial image, because the input naturally carries less information, and images corrupted with down-sampling and blur would interfere the facial analysis procedure. Face hallucination [6–13], a task that super-resolves facial images, provides a viable means for improving low-res face processing and analysis, e.g. person identification in surveillance videos and facial image enhancement. Prior on face structure, or face spatial configuration, is pivotal for face hallucination [6,7,12]. The availability of such prior distinguishes the face hallucination task from the general image super-resolution problem [14–21], where the latter lacks of such global prior to facilitate the inference. In this study, we extend the notion of prior to pixel-wise dense face correspondence field. We observe that an informative prior provides a strong semantic guidance that enables face hallucination even from a very low resolution. Here the dense correspondence field is Throughout this paper, we use the inter-ocular distance measured in pixels (denoted as pxIOD), to concisely and unambiguously represent the face size. c Springer International Publishing AG 2016  B. Leibe et al. (Eds.): ECCV 2016, Part V, LNCS 9909, pp. 614–630, 2016. DOI: 10.1007/978-3-319-46454-1 37

Deep Cascaded Bi-Network for Face Hallucination

615

Fig. 1. (a) The original high-res image. (b) The low-res input with a size of 5pxIOD. (c) The result of bicubic interpolation. (d) An overview of the proposed face hallucination framework. The solid arrows indicate the hallucination step that hallucinates the face with spatial cues, i.e. the dense correspondence field. The dashed