Jack Saunders – Medium

Jack Saunders

Jack Saunders

Breaking Down Synthesia 2.0

We take a look at the tech that's underpinning the impressive new launch.

Jun 24

Breaking Down Synthesia 2.0

Jun 24

Jack Saunders
in
Towards Data Science

Scale Is All You Need for Lip-Sync?

Alibaba’s EMO and Microsoft’s VASA-1 are crazy good. Let’s break down how they work.

Jun 7

Scale Is All You Need for Lip-Sync?

Jun 7

Jack Saunders

The Definitive Guide to Lip Sync Companies

There are now so many lip-sync/AI Avatar/ Talking Face Generation Companies. Who is who?

May 25

The Definitive Guide to Lip Sync Companies

May 25

Jack Saunders
in
Towards Data Science

Gaussian Head Avatars: A Summary

There has been a recent explosion of Gaussian Splatting papers and the avatar space is no exception. How do they work and are they going to…

Dec 19, 2023

Gaussian Head Avatars: A Summary

Dec 19, 2023

Jack Saunders
in
Towards AI

READ Avatars: Realistic Emotion-controllable Audio Driven Avatars

Adding Emotional Control to Audio-Driven Deepfakes

Aug 25, 2023

READ Avatars: Realistic Emotion-controllable Audio Driven Avatars

Aug 25, 2023

Jack Saunders
in
Towards AI

DAE Talking: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder

Diffusion Models + Lots of Data = Practically Perfect Talking Head Generation

Jul 14, 2023

DAE Talking: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder

Jul 14, 2023

Jack Saunders
in
Towards AI

Towards Generating Ultra-High Resolution Talking-Face Videos with Lip-Synchronization

The holy grail of deepfake models is the person-generic model. So far no person-generic model has been of high visualquality, this paper is.

May 27, 2023

A 3 by 3 grid showing results of this method on a section of silence. The columns represent a sequence of frames over time. The top row shows the real video. The middle row shows Wav2Lip. It has obvious artefacts and the lips are moving. The bottom row is this paper. It looks much higher quality and the lips are shut, this is good because the image is meant to be showing silence.

May 27, 2023

Jack Saunders
in
Towards Data Science

Should Deepfakes be Open-Sourced?

The purpose of this article is to try and start a conversation about open-sourcing in deepfake research. I cover the pros and cons.

May 25, 2023

Should Deepfakes be Open-Sourced?

May 25, 2023

Jack Saunders

Person-Specific Deepfakes with 3D Morphable Models

While person-generic models such as Wav2Lip are incredibly versatile and work out of the box with any face and any audio, they still lack…

May 11, 2023

Person-Specific Deepfakes with 3D Morphable Models

May 11, 2023

Jack Saunders

Wav2Lip: Generalized Lip Sync Models

Wav2Lip is one of the most popular lip sync models. In this article we explore how it works and analyse its potential for improvment.

Apr 27, 2023

Wav2Lip: Generalized Lip Sync Models

Apr 27, 2023

Jack Saunders

Jack Saunders

PhD student researching deep learning for digital humans, particularly on style and speech in human facial animation

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams