1 |
AnyFace: Free-style Text-to-Face Synthesis and Manipulation ...
|
|
|
|
Abstract:
Existing text-to-image synthesis methods generally are only applicable to words in the training dataset. However, human faces are so variable to be described with limited words. So this paper proposes the first free-style text-to-face method namely AnyFace enabling much wider open world applications such as metaverse, social media, cosmetics, forensics, etc. AnyFace has a novel two-stream framework for face image synthesis and manipulation given arbitrary descriptions of the human face. Specifically, one stream performs text-to-face generation and the other conducts face image reconstruction. Facial text and image features are extracted using the CLIP (Contrastive Language-Image Pre-training) encoders. And a collaborative Cross Modal Distillation (CMD) module is designed to align the linguistic and visual features across these two streams. Furthermore, a Diverse Triplet Loss (DT loss) is developed to model fine-grained features and improve facial diversity. Extensive experiments on Multi-modal CelebA-HQ and ...
|
|
Keyword:
Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2203.15334 https://dx.doi.org/10.48550/arxiv.2203.15334
|
|
BASE
|
|
Hide details
|
|
2 |
Optimizing the Desorption Technology of Total Flavonoids of Ginkgo Biloba from Separating Materials of Activated Carbon
|
|
|
|
In: ACS Omega (2021)
|
|
BASE
|
|
Show details
|
|
3 |
A Spelling Paradigm With an Added Red Dot Improved the P300 Speller System Performance
|
|
|
|
In: Front Neuroinform (2020)
|
|
BASE
|
|
Show details
|
|
4 |
Measurement of $W^{\pm}$-boson and $Z$-boson production cross-sections in $pp$ collisions at $\sqrt{s}=2.76$ TeV with the ATLAS detector
|
|
|
|
BASE
|
|
Show details
|
|
6 |
The English language used by the Chinese: A new variety of English?
|
|
|
|
BASE
|
|
Show details
|
|
14 |
The Motivation of Chinese Learners of English in a Foreign and Second Language Context
|
|
Li, Qi. - : ResearchSpace@Auckland, 2011
|
|
BASE
|
|
Show details
|
|
|
|