1. Face hallucination from low quality images using definition-scalable inference
- Author
-
Li Wang, Zhuohao Mai, Xiao Hu, Zhao Yang, Shao-Hu Peng, and Peirong Ma
- Subjects
Face hallucination ,business.industry ,Computer science ,media_common.quotation_subject ,Scale-invariant feature transform ,Inference ,Pattern recognition ,02 engineering and technology ,01 natural sciences ,Similarity (network science) ,Artificial Intelligence ,Hallucinating ,Face (geometry) ,0103 physical sciences ,Signal Processing ,Scalability ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Quality (business) ,Computer Vision and Pattern Recognition ,Artificial intelligence ,010306 general physics ,business ,Software ,media_common - Abstract
To hallucinate super-resolution (super-res) face from a real low-quality face, a super-resolution technique based on definition-scalable inference (SRDSI) is proposed in this paper. In the proposed strategy, all high-res labeled faces are first decomposed into basic faces and enhanced faces to train a basic face and an enhanced face inferring model, and then two inferring models are used to hallucinate super-res basic face with low-definition and enhanced faces with high-frequency information from a single low-res face. Finally, the basic face is merged with its enhanced face into a super-res face with high-definition. In addition, this paper employs SIFT key-points to evaluate the similarity between the super-res face and its high-res labeled face. Experimental results show that SRDSI can effectively recover more structural information as well as SIFT key-points from real low-res faces and achieves better performance than state-of-the-art super-resolution techniques in terms of both visual and objective quality.
- Published
- 2019