태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Blind face restoration aims at recovering high-quality faces from the low-quality counterparts suffering from unknown degradation, such as low-resolution, noise, blur, compression artifacts, etc. When applied to real-world scenarios, it becomes more challenging, due to more complicated degradation, diverse poses and expressions.
Description source: Towards Real-World Blind Face Restoration with Generative Facial Prior
Image source: Towards Real-World Blind Face Restoration with Generative Facial Prior
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
CelebFaces Attributes dataset contains 202,599 face images of the size 178×218 from 10,177 celebrities, each annotated with 40 binary labels indicating facial attributes like hair color, gender and age. Source: Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention Image Source: http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html
The CelebA-HQ dataset is a high-quality version of CelebA that consists of 30,000 images at 1024×1024 resolution. Source: IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis Image Source: https://github.com/tkarras/progressive_growing_of_gans
The LFW dataset contains 13,233 images of faces collected from the web. This dataset consists of the 5749 identities with 1680 people with two or more images. In the standard LFW evaluation protocol the verification accuracies are reported on 6000 face pairs. Source: A Performance Evaluation of Loss Functions for Deep Face Recognition Image Source: http://vis-www.cs.umass.edu/lfw
WIDER is a dataset for complex event recognition from static images. As of v0.1, it contains 61 event categories and around 50574 images annotated with event class labels.
This Wider-Test-200 dataset is introduced in the following paper: "Towards Unsupervised Blind Face Restoration using Diffusion Prior" Please visit our website and refer to our paper for more information on the dataset and our method: https://dt-bfr.github.io/
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.