Talking Head Generation

13 papers with code • 7 benchmarks • 2 datasets

Talking head generation is the task of generating a talking face from a set of images of a person.

( Image credit: Few-Shot Adversarial Learning of Realistic Neural Talking Head Models )

Most implemented papers

Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

vincent-thevenin/Realistic-Neural-Talking-Head-Models ICCV 2019

In order to create a personalized talking head model, these works require training on a large dataset of images of a single person.

MakeItTalk: Speaker-Aware Talking-Head Animation

yzhou359/MakeItTalk 27 Apr 2020

We present a method that generates expressive talking heads from a single facial image with audio as the only input.

A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild

Rudrabha/Wav2Lip 23 Aug 2020

However, they fail to accurately morph the lip movements of arbitrary identities in dynamic, unconstrained talking face videos, resulting in significant parts of the video being out-of-sync with the new audio.

ReenactGAN: Learning to Reenact Faces via Boundary Transfer

wywu/ReenactGAN ECCV 2018

A transformer is subsequently used to adapt the boundary of source face to the boundary of target face.

0-Step Capturability, Motion Decomposition and Global Feedback Control of the 3D Variable Height-Inverted Pendulum

GabrielEGC/IHMC-Robotics 12 Dec 2019

We also prove that the 3D VHIP with Fixed CoP is the same as its 2D version, and we generalize controllers working on the 2D VHIP to the 3D VHIP.

What comprises a good talking-head video generation?: A Survey and Benchmark

lelechen63/talking-head-generation-survey 7 May 2020

In this work, we present a carefully-designed benchmark for evaluating talking-head video generation with standardized dataset pre-processing strategies.

Talking-head Generation with Rhythmic Head Motion

lelechen63/Talking-head-Generation-with-Rhythmic-Head-Motion 16 Jul 2020

When people deliver a speech, they naturally move heads, and this rhythmic head motion conveys prosodic information.

Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars

saic-violet/bilayer-model ECCV 2020

The texture image is generated offline, warped and added to the coarse image to ensure a high effective resolution of synthesized head views.

Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation

FuxiVirtualHuman/Write-a-Speaker 16 Apr 2021

To be specific, our framework consists of a speaker-independent stage and a speaker-specific stage.

Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text

tpulkit/txt2vid 26 Jun 2021

Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure.