Notes:
StyleGAN, developed by NVIDIA, is a state-of-the-art generative adversarial network (GAN) architecture that produces high-quality, realistic images. Introduced to the machine learning community in 2018, this model represents a significant advancement in image generation, particularly in the generation of facial images. StyleGAN’s unique design incorporates a style-based generator architecture, which allows for the nuanced control of generated images, making it possible to manipulate different attributes at various levels of detail. Several works have leveraged its capabilities in diverse applications ranging from medical imaging to art generation, and even for text-to-image synthesis. Furthermore, the model has been iteratively improved upon, with versions like StyleGAN2 and StyleGAN3 addressing various challenges and enhancing its capabilities. This robust and versatile model has seen widespread adoption, especially in applications that require high-resolution and hyper-realistic image synthesis.
Resources:
Wikipedia:
References:
- DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Rendering (2022)
- Depth-Aware Generative Adversarial Network for Talking Head Video Generation (2022)
- Dynamic facial animation of Chinese Shaanxi Xi’an dialect talking head (2022)
- Expressive Talking Head Generation with Granular Audio-Visual Control (2022)
- Free-HeadGAN: Neural Talking Head Synthesis with Explicit Gaze Control (2022)
- Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis (2022)
- StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation (2022)
- Talking Head Generation Driven by Speech-Related Facial Action Units and Audio-Based on Multimodal Representation Fusion (2022)
- Talking Head from Speech Audio using a Pre-trained Image Generator (2022)
- Talking Heads “This must be the plase” (2022)
- Talking Heads: Bone conduction facilitates self-other voice discrimination (2022)
- Talking-heads attention-based knowledge representation for link prediction (2022)
- Text2video: Text-Driven Talking-Head Video Synthesis with Personalized Phoneme-Pose Dictionary (2022)
- Towards MOOCs for Lip Reading: Using Synthetic Talking Heads to Train Humans in Lipreading at Scale (2022)
See also:
100 Best Pinscreen Videos | Talking Heads
[38x Oct 2022]
- 52cv/iccv-2021-papers
- amrzv/awesome-colab-notebooks: collection of google colaboratory notebooks for fast and easy experiments
- amusi/eccv2022-papers-with-code: eccv 2022
- bbvanexttechnologies/tools-generation-detection-synthetic-content: compilation of the state of the art of tools, articles, forums and links of interest to generate and detect any type of synthetic content using deep learning.
- chanchichoi/awesome-face_recognition: papers about face detection; face alignment; face recognition && face identification && face verification && face representation; face reconstruction; face tracking; face super-resolution && face deblurring; face generation && face synthesis; face transfer; face anti-spoofing; face retrieval;
- chanchichoi/awesome-gan-papers: papers and codes about gan
- clpeng/awesome-face-forgery-generation-and-detection: a curated list of articles and codes related to face forgery generation and detection.
- daddyjin/awesome-facereenactment: papers about face reenactment/talking face generation
- darrenpan/awesome-eccv2022-low-level-vision: a collection of papers and codes in eccv2022 about low level vision
- deepvtuber/openvtuber: openvtuber
- dwctod/cvpr2022-papers-with-code-demo
- dwctod/eccv2022-papers-with-code-demo
- eyaler/avatars4all: live real-time avatars from your webcam in the browser. no dedicated hardware or software installation needed. a pure google colab wrapper for live first-order-motion-model, aka avatarify in the browser. and other colabs providing an accessible interface for using fomm, wav2lip and liquid-warping-gan with your own media and a rich gui.
- felime/audiostylenet: this repository contains the code for my master thesis on emotion-aware facial animation
- gbstack/cvpr-2022-papers: cvpr 2022 papers with code
- happy-jihye/awesome-gan-papers: generative adversarial networks : paper, pytorch-code, review(korean)
- harlanhong/awesome-talking-head-generation
- josephpai/awesome-talking-face: a curated list of resources dedicated to talking face.
- kangyeolk/animeceleb: official implementation of “animeceleb: large-scale animation celebheads dataset for head reenactment” (eccv 2022)
- kyugorithm/til: today i learned
- mrzzm/hdtf: the dataset and code for “flow-guided one-shot talking face generation with a high-resolution audio-visual dataset”
- p-geon/gansurvey
- pedro-abundio-wang/gans: generative adversarial networks
- rlczddl/awesome-3d-human-reconstruction
- rotemtzaban/stit
- senhe/cool-gan-works
- seriallain3170/awesomeanimeresearch: papers, repository and other data about anime or manga research. please let me know if you have information that the list does not include.
- someonedistant/sun: self using notes of tricks, techniques and paper.
- tikhonovpavel/talking-head-stylegan
- weihaox/awesome-neural-rendering: a collection of resources on neural rendering.
- ykk648/awesome-papers-are-all-you-need: digitalhuman-releated papers and codes.
- yunjinpark/awesome_talking_face_generation
- yutong-zhou-cv/awesome-text-to-image: a survey on text-to-image generation/synthesis
- zhaishuyan/paperlist: organize a list of papers
- zhangzjn/awesome-face-generation: basic gan frameworks and approaches for face swap, reenactment, and stylizing.
- zhusiling/super-resolution-with-gan