paper-with-me

홈 › Papers

Robust Multi-Image Based Blind Face Hallucination

2015-06-01 · CVPR 2015 6 · Yonggang Jin, Christos-Savvas Bouganis

This paper proposes a robust multi-image based blind face hallucination framework to super-resolve LR faces. The proposed framework first estimates both blurring kernel and transformations of multiple LR faces by robust deblurring and registration in PCA subspace. A patch-wise mixture of probabilistic PCA prior is then incorporated for face super-resolution. Previous work on face SR using PCA prior can be viewed as special cases of the framework. Experimental results in both simulated and real LR sequences demonstrate very promising performance of the proposed method.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DeblurringFace HallucinationHallucinationSuper-Resolution

Similar Papers 제목 키워드 기반

Efficient and robust 3D blind harmonization for large domain gaps

2025-04-30 · Hwihun Jeong, Hayeon Lee, Se Young Chun, Jongho Lee

Blind harmonization has emerged as a promising technique for MR image harmonization to achieve scale-invariant representations, requiring only target domain data (i.e., no source domain data necessary). However, existing…

HallucinationImage Harmonization

DiffMAC: Diffusion Manifold Hallucination Correction for High Generalization Blind Face Restoration

2024-03-15 · Nan Gao, Jia Li, Huaibo Huang, Zhi Zeng 외

Blind face restoration (BFR) is a highly challenging problem due to the uncertainty of degradation patterns. Current methods have low generalization across photorealistic and heterogeneous domains. In this paper, we prop…

AttributeBlind Face RestorationHallucination

Semantic Similarity is a Spurious Measure of Comic Understanding: Lessons Learned from Hallucinations in a Benchmarking Experiment

2026-03-02 · Christopher Driggers-Ellis, Nachiketh Tibrewal, Rohit Bogulla, Harsh Khanna 외 arxiv

A system that enables blind or visually impaired users to access comics/manga would introduce a new medium of storytelling to this community. However, no such system currently exists. Generative vision-language models (V…

Semantic Similarity

Blind Image Super-Resolution with Spatial Context Hallucination

2020-09-25 · Dong Huo, Yee-Hong Yang

Deep convolution neural networks (CNNs) play a critical role in single image super-resolution (SISR) since the amazing improvement of high performance computing. However, most of the super-resolution (SR) methods only fo…

Blind Super-ResolutionDeblurringDenoisingHallucination+2

FH-GAN: Face Hallucination and Recognition using Generative Adversarial Network

2019-05-16 · Bayram Bayramli, Usman Ali, Te Qi, Hongtao Lu

There are many factors affecting visual face recognition, such as low resolution images, aging, illumination and pose variance, etc. One of the most important problem is low resolution face images which can result in bad…

Face HallucinationFace RecognitionGenerative Adversarial NetworkHallucination