Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

Face Hallucination | State-of-the-Art

computer-vision

Face Hallucination

3260 papers • 126 benchmarks • 313 datasets

Face hallucination is the task of generating high-resolution (HR) facial images from low-resolution (LR) inputs. ( Image credit: Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in face-hallucination

Trend

Dataset

Best Model

Actions

FFHQ 512 x 512 - 16x upscaling

FFHQ 512 x 512 - 16x upscaling

Libraries

i

Use these libraries to find face-hallucination models and implementations

Datasets

FFHQ

EDFace-Celeb-1M

EDFace-Celeb-1M

KID-F

Subtasks

No subtasks available.

Most implemented papers

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

Y. Qiao, Chen Change Loy, Xiaoou Tang, Chao Dong, Xintao Wang, Jinjin Gu, Yihao Liu, Ke Yu, Shixiang Wu•Fri Aug 31 2018

This work thoroughly study three key components of SRGAN – network architecture, adversarial loss and perceptual loss, and improves each of them to derive an Enhanced SRGAN (ESRGAN), which achieves consistently better visual quality with more realistic and natural textures than SRGAN.

4394

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

C. Rudin, Sachit Menon, Alexandru Damian, Shijia Hu, Nikhil Ravi•Sat Mar 07 2020

This work presents a novel super-resolution algorithm, PULSE (Photo Upsampling via Latent Space Exploration), which generates high-resolution, realistic images at resolutions previously unseen in the literature, and outperforms state-of-the-art methods in perceptual quality at higher resolutions and scale factors than previously possible.

613 0

HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment

Siwei Ma, Wen Gao, Peiran Ren, Lingbo Yang, Chang Liu, Pan Wang, Shanshe Wang•Sun May 10 2020

HiFaceGAN, a multi-stage framework containing several nested CSR units that progressively replenish facial details based on the hierarchical semantic guidance extracted from the front-end content-adaptive suppression modules, is presented.

146 0

DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-Resolution

Radu Timofte, Andrés Romero, Marcel C. Bühler•Wed Apr 08 2020

This work proposes a novel framework, DeepSEE, for Deep disentangled Semantic Explorative Extreme super-resolution, and is the first method to leverage semantic maps for explorative super- resolution, and validates DeepSEE for up to 32x magnification and exploration of the space ofsuper-resolution.

34 0

Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination

Jiayi Ma, Junjun Jiang, Jinhui Hu, Suhua Tang•Thu May 31 2018

This paper proposes a general face hallucination method that can integrate model-based optimization and discriminative inference, and develops a high-frequency details compensation method by dividing the face image to facial components and performing face hallucinations in a multi-layer neighbor embedding manner.

54 0

Context-Patch Face Hallucination Based on Thresholding Locality-Constrained Representation and Reproducing Learning

K. Aizawa, Jiayi Ma, Junjun Jiang, Akiko Aizawa, Suhua Tang•Sun Sep 02 2018

This paper incorporates the contextual information of the image patch and proposes a powerful and efficient context-patch-based face hallucination approach, namely, thresholding locality-constrained representation and reproducing learning (TLcR-RL).

55 0

SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination

Chih-Chung Hsu, Chia-Wen Lin, Weng-Tai Su, Gene Cheung•Sat Jul 21 2018

A Siamese GAN to reconstruct HR faces that visually resemble their corresponding identities that significantly outperforms existing face hallucination GANs in objective face verification performance while achieving promising visual-quality reconstruction.

79 0

Face Hallucination via Split-Attention in Split-Attention Network

T. Lu, Yuanzhi Wang, Yanduo Zhang, Yu Wang, Wei Liu, Zhongyuan Wang, Junjun Jiang•Wed Oct 21 2020

Experimental results on face hallucination and face recognition unveil that the proposed method not only significantly improves the clarity of hallucinated faces, but also encourages the subsequent face recognition performance substantially.

86 0

Deep Learning-based Face Super-resolution: A Survey

Jiayi Ma, Junjun Jiang, Xianming Liu, Chenyang Wang•Sun Jan 10 2021

This survey presents a comprehensive review of deep learning-based FSR methods in a systematic manner and roughly categorizes existing methods according to the utilization of facial characteristics.

147 0

Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN

Vishal M. Patel, Rakhil Immidisetti, Shuowen Hu•Mon Apr 12 2021

This work introduces the task of thermal- to-visible face verification from low-resolution thermal images, and proposes Axial-Generative Adversarial Network (Axial-GAN) to synthesize high-resolution visible images for matching.

20 0

Adding a benchmark result helps the community track progress.