DeepFakes

Generative AI

Microsoft’s New AI: Virtual Humans Became Real! 🤯

Two Minute Papers examines the paper “3D Face Reconstruction with Dense Landmarks” in the following video. Fun fact, I remember seeing an early version of this research at the last MLADS conference I attended in 2019.

Read More
Deep Fakes Generative AI

This New AI Makes DeepFakes for Animation Movies! 🧑‍🎨

Two Minute Papers examines the paper “Stitch it in Time: GAN-Based Facial Editing of Real Videos” in the video below. Chapters 00:00 Intro 00:23 This new work is different 00:50 Obama speech reimagined 01:26 Temporal coherence 02:41 Not perfect 02:56 A DeepFake of … me! 03:58 It works on animated characters too 04:30 So much […]

Read More
AI Computer Vision Facial Recognition Research

Microsoft’s AI Understands Humans Despite Never Seeing One

It looks like synthetic data has its day and how! Two Minute Papers explores the paper “Fake It Till You Make It – Face analysis in the wild using synthetic data alone” in the video below.

Read More
AI Deep Fakes

This AI Makes "Audio Deepfakes"

Two Minute Papers explores the paper “Neural Voice Puppetry: Audio-driven Facial Reenactment“. The blog post on #deepfakes is available here: https://www.wandb.com/articles/improving-deepfake-performance-with-data

Read More
Generative AI

Now Everybody Can Make DeepFakes

Two Minute Papers takes a look at the paper “First Order Motion Model for Image Animation” and its source code are available here: Paper: https://aliaksandrsiarohin.github.io/first-order-model-website/ Colab notebook: https://colab.research.google.com/github/AliaksandrSiarohin/first-order-model/blob/master/demo.ipynb

Read More
AI Generative AI

Can We Detect Neural Image Generators?

Two Minute Papers examines the paper “CNN-generated images are surprisingly easy to spot…for now.”

Read More
Deep Fakes Generative AI

AI Video Synthesis

Two Minute Papers examines the paper “Few-shot Video-to-Video Synthesis” in this video.

Read More
AI Generative AI

AI Animation Tutorial

Ben Marriott uses the style-transfer software EbSynth on animated footage to see if you really can change the style using a single reference frame. EbSynth is technically not an artificial intelligence software, It uses style transfer to get its results. I put AI in the title and thumbnail because it does what most people would […]

Read More
AI Deep Fakes

DeepFake Detector AIs

Two Minute Papers explores the counter work to deep fakes with the paper “FaceForensics++: Learning to Detect Manipulated Facial Images.”

Read More