2018
DOI: 10.1007/978-3-030-01240-3_14
|View full text |Cite
|
Sign up to set email alerts
|

Face Super-Resolution Guided by Facial Component Heatmaps

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
153
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 214 publications
(153 citation statements)
references
References 33 publications
0
153
0
Order By: Relevance
“…However, most existing methods for general natural images are still sensitive to the degradation profile [9] and exhibit poor generalization over unconstrained testing conditions. For category-specific [2] (face) restoration, it is commonly believed that incorporating external guidance on facial prior would boost the restoration performance, such as semantic prior [38], identity prior [12], facial landmarks [4] [5] or component heatmaps [60]. In particular, Li et.al.…”
Section: Blind Face Restorationmentioning
confidence: 99%
See 1 more Smart Citation
“…However, most existing methods for general natural images are still sensitive to the degradation profile [9] and exhibit poor generalization over unconstrained testing conditions. For category-specific [2] (face) restoration, it is commonly believed that incorporating external guidance on facial prior would boost the restoration performance, such as semantic prior [38], identity prior [12], facial landmarks [4] [5] or component heatmaps [60]. In particular, Li et.al.…”
Section: Blind Face Restorationmentioning
confidence: 99%
“…It is often challenging to reconstruct image contents from artifacts without degradation prior, necessitating additional guidance information such as categorial [2] or structural prior [5] to facilitate the replenishment of faithful and photo-realistic details. For blind face restoration [35] [6], facial landmarks [4], parsing maps [54], and component heatmaps [60] are typically utilized as external guidance labels. In particular, Li et.al.…”
Section: Introductionmentioning
confidence: 99%
“…In particular, face super-resolution (SR), wherein visually pleasing photorealistic results might be more important than conventional quantitative scores, is a more specific and difficult problem than general SISR. Recent methods have employed various facial geometry priors, e.g., facial landmarks, parsing maps, and 3D morphable models, to reconstruct HR facial images [11], [12]. Moreover, additional tasks, such as estimating the face region mask, facial landmark heatmaps, and parsing maps, improve the quality of the reconstructed HR facial images [13].…”
Section: Introductionmentioning
confidence: 99%
“…It is desirable to reconstruct high-resolution images from lowresolution images by super-resolution (SR) algorithms [1]. According to recent SR research, these methods are classified into two types: interpolation-based approaches [2]- [5] and learning-based approaches [6]- [43]. The interpolation-based approaches estimate statistical prior knowledge from natural images to produce HR images, but there are inherent limitations when dealing with the increase in the magnification factor.…”
mentioning
confidence: 99%
“…Huang et al [42] proposed a wavelet-based neural network to conduct the face hallucination task, which simultaneously takes into account the local texture details and global topology information of human faces. Yu et al [43] proposed a multi-task network that consists of upsampling branch and facial component heatmaps estimation branch. The upsampling branch is guided by the heatmaps in the reconstruction for preserving face structure.…”
mentioning
confidence: 99%