DeepWriting: Making Digital Ink Editable via Deep Generative Modeling: #ML #Generative
Project: https://ait.ethz.ch/projects/2018/deepwriting/
Code: https://github.com/emreaksan/deepwriting
DeepWriting: Making Digital Ink Editable via Deep Generative Modeling: #ML #Generative
Project: https://ait.ethz.ch/projects/2018/deepwriting/
Code: https://github.com/emreaksan/deepwriting
How Music Generated by Artificial Intelligence Is Reshaping -- Not Destroying -- The Industry: https://www.billboard.com/biz/articles/news/legal-and-management/8350905/how-music-generated-by-artificial-intelligence-is #Music #ML #Generative
ResGAN: Speech synthesis from MFCC sequences with generative adversarial networks:
Paper: https://arxiv.org/abs/1804.00920
Samples: https://users.aalto.fi/~ljuvela/mfcc_vocoding/
Code: https://github.com/ljuvela/ResGAN
My favorite #ML project of the month. A real world example of how computation can help reduce climate change related pressures and a case study for #FFHCI:
AI helps grow 6 billion roaches at China's largest breeding site: https://www.cnet.com/news/ai-helps-grow-6b-roaches-at-chinas-largest-breeding-facility/
"The system ensures an optimal growth environment for the cockroaches, which are eventually crushed to make a "healing potion" that cures ailments like stomachache"
Dream Lens: "Exploration and Visualization of Large-Scale Generative Design Datasets" - by Autodesk Research: https://www.autodeskresearch.com/publications/dreamlens
Generative design browsers are a key (missing) component for making generative processes go mainstream. The "Dream Lens" browser combines many relevant ideas, applicable to generative design tasks in other creative disciplines as well.
"Artificial Intelligence — The Revolution Hasn’t Happened Yet" - talk by Michael Jordan: #ML
https://medium.com/@mijordan3/artificial-intelligence-the-revolution-hasnt-happened-yet-5e1d5812e1e7 call to "broaden our scope, tone down the hype and recognize the serious challenges ahead."
"Shared Autonomy via Deep Reinforcement Learning": #ML
http://bair.berkeley.edu/blog/2018/04/18/shared-autonomy/
Deep Painterly Harmonization - Paper: https://arxiv.org/abs/1804.03189
Code: https://github.com/luanfujun/deep-painterly-harmonization #ML #Generative #Art
mememoji - A facial expression classification system that recognises 6 basic emotions:
Code: https://github.com/JostineHo/mememoji #ML #Emotion
"Generating Sentences from a Continuous Space" - PyTorch Implementation: https://github.com/timbmg/Sentence-VAE paper: https://arxiv.org/abs/1511.06349 #ML
Visual Analysis of Clothing Style Trends in TV News:
code: https://github.com/sola777/video-analysis #ML
Text-independent voice vectors: "Which Hollywood stars is most similar to my voice?"
code: https://github.com/andabi/voice-vector
demo: https://voice-vector-web.andabi.me/ #ML #Music
The Conversation: Deep Audio-Visual Speech Enhancement:
https://arxiv.org/abs/1804.04121 #ML
KidPen: A Stroke-based Method for Kid-style Sketches Synthesis from Photos:
https://dl.acm.org/citation.cfm?id=3149434 (paywalled. force open access version: https://sci-hub.tw/https://dl.acm.org/citation.cfm?id=3149434) #ML #Generative
Two-Stream Convolutional Networks for Dynamic Texture Synthesis: #ML #Generative
Paper: https://arxiv.org/abs/1706.06982v4
Project: https://ryersonvisionlab.github.io/two-stream-projpage/
Code: https://github.com/ryersonvisionlab/two-stream-dyntex-synth
Speech and Facial Animation - comparison of technical papers: #ML
Video Based Reconstruction of 3D People Models: https://arxiv.org/abs/1803.04758
Marilyn Monroe Deepfake:
Obama Deepfake:
Putin Deepfake:
Nic Cage Deepfakes mini compilation:
Steve Buscemi as Sharon Stone, Basic Instinct:
Putin Trump Deepfake:
Donald Trump as Michael Scott:
Merkel Trump Deepfake:
A New Hope but Obi Wan is played by Ewan McGregor:
Matt Damon:
Starttrek Picard :
Terminator:
I Interviewed my Top 5 Favorite TechTubers:
How I used DeepFakes to spoof Techtubers:
Exploring DeepFakes: https://hackernoon.com/exploring-deepfakes-20c9947c22d9
MUNIT: Multimodal unsupervised image-to-image translation. Learn to translate one input dog image to a distribution of cat images without paired training data. #ML #Generative
Paper: https://arxiv.org/abs/1804.04732 - Code: github.com/nvlabs/munit
Tensorflow implementation: https://github.com/taki0112/MUNIT-Tensorflow