Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
Awesome-DeepFake-Learning
The approach I work on DeepFake.
https://github.com/Billy1900/Awesome-DeepFake-Learning
Last synced: 3 days ago
JSON representation
-
1. Intuitive Learning
- News From CNN
- 10 DeepFake Examples
- An Introduction to DeepFakes
- Deeptrace - Zoo/tree/master/the-state-of-deepfakes)
- **website**
-
2. Survey Paper
-
3. Curated lists
-
4. Deepfakes Datasets
-
5. Generation of synthetic content
-
5.1 Generation Text
- Grover - - both generation and detection. However, it probably can also be used for other generation tasks. | [https://grover.allenai.org/](https://grover.allenai.org/) | [](https://github.com/rowanz/grover)|
- gpt-2xy - 2 User Interface based on HuggingFace's Pytorch Implementation | https://gpt2.ai-demo.xyz/ | [](https://github.com/NaxAlpha/gpt-2xy) |
- CTRL
- LEO
- Big Bird - checked and substantive content. | [BigBirdDemo](https://run.bigbird.dev/auth/login)| N/A
- GPT-2 Neural Network Poetry
- aitextgen - based AI training and generation using GPT-2.| [Demo](https://git.io/JfuXR) | [](https://github.com/minimaxir/aitextgen)
- GPT-3 - 3: Language Models are Few-Shot Learners | N/A | [](https://github.com/openai/gpt-3)
- Language Models are Unsupervised Multitask Learners
- Saliency Maps Generation for Automatic Text Summarization
- Automatic Conditional Generation of Personalized Social Media Short Texts
- Neural Text Generation in Stories Using Entity Representations as Context
- DeepTingle
- GPT-3: Language Models are Few-Shot Learners
- Evaluation of Text Generation: A Survey
- NotRealNews
- BotPoet
- TheseLyricsDoNotExist
- ThisResumeDoesNotExist
- ThisArtWorkDoesnotExist
- BoredHumans
- A.ttent.io
- ThisEpisodeDoesNotExist
- awesome-text-generation
- Awesome GPT-3
-
5.2 Generation Audio
- Real-Time-Voice-Cloning - time | https://www.youtube.com/watch?v=-O_hYhToKoA | [](https://github.com/CorentinJ/Real-Time-Voice-Cloning)
- Lyrebird
- Descrypt
- Common Voice
- Resemble.ai
- TacoTron - to-end speech synthesis system by Google. | [Demo](https://google.github.io/tacotron/publications/prosody_prior/index.html) | [](https://github.com/google/tacotron)
- 15.ai - to-speech synthesis with minimal data. | [Demo](https://fifteen.ai/examples) | N/A
- Neural Voice Cloning with a Few Samples
- Data Efficient Voice Cloning for Neural Singing Synthesis
- Efficient Neural Audio Synthesis
- Score and Lyrics-free Singing Voice Generation
- Rave.dj
-
5.3 Generation Images
- StyleGAN - level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images (e.g., freckles, hair), and it enables intuitive, scale-specific control of the synthesis. The new generator improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation. | https://www.youtube.com/watch?v=kSLJriaOumA | [](https://github.com/NVlabs/stylegan)
- StyleGAN2 - NJtV9Jvp0 | [](https://github.com/NVlabs/stylegan2)
- DG-Net - identification | https://www.youtube.com/watch?v=ubCrEAIpQs4 | [](https://github.com/NVlabs/DG-Net)
- GANSpace
- StarGAN v2 - Official PyTorch Implementation (CVPR 2020) | https://youtu.be/0EVh5Ki4dIY | [](https://github.com/clovaai/stargan-v2)
- Image GPT - gpt)](https://github.com/openai/image-gpt)
- FQ-GAN - GAN | http://40.71.23.172:8888 | [](https://github.com/YangNaruto/FQ-GAN)
- EHM_Faces - quality, realistic ice hockey player portraits. Primarily meant for the game Eastside Hockey Manager (EHM), this project can generate portraits either one-at-a-time or in batches (the resulting batches are called facepacks). | N/A | [](https://github.com/colinrsmall/ehm_faces)
- Rewriting a Deep Generative Model - interface.ipynb) | [](https://github.com/davidbau/rewriting)
- Semantic Image Synthesis with SPADE - Adaptive Normalization in CVPR. | [Demo Page](https://nvlabs.github.io/SPADE/) | [](https://github.com/NVlabs/SPADE)
- A Style-Based Generator Architecture for Generative Adversarial Networks
- Analyzing and Improving the Image Quality of StyleGAN
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
- Complement Face Forensic Detection and Localization with Facial Landmarks
- Joint Discriminative and Generative Learning for Person Re-identification
- Image2StyleGAN++: How to Edit the Embedded Images?
- StyleGAN2 Distillation for Feed-forward Image Manipulation
- Generative Pretraining from Pixels
- Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition
- StarGAN v2: Diverse Image Synthesis for Multiple Domains
- Feature Quantization Improves GAN Training
- High-Resolution Neural Face Swapping for Visual Effects
- Improving Style-Content Disentanglement in Image-to-Image Translation
- Rewriting a Deep Generative Model
-
Programming Languages
Categories
Keywords
deep-learning
5
pytorch
4
text-generation
2
dukemtmc-reid
1
dg-net
1
cuhk-np
1
apex
1
voice-cloning
1
tts
1
tensorflow
1
python
1
neural-text-generation
1
natural-language-processing
1
fake-news-classification
1
tracking-by-detection
1
tracking
1
segmentation
1
papers
1
paper-collection
1
optical-flow
1
object-detection
1
detection
1
vision
1
research
1
machine-learning
1
hci
1
graphics
1
gans
1
stargan-v2
1
image-to-image-translation
1
generative-models
1
cvpr2020
1
interactive-visualizations
1
image-generation
1
generative-adversarial-network
1
gan
1
re-identification
1
person-reidentification
1
person-reid
1
open-reid
1
msmt17
1
market-1501
1
image-search
1
image-retrieval
1
code-collection
1