Abe Davis

MIT PhD / Stanford Postdoc

Winter/Spring 2019

I am traveling most of Feb-April and may be slow responding to messages. I'll try to answer what I can, but may miss some. I apologize in advance, and will hopefully be better about it when things aren't as hectic later in the year.

About Me

I am a computer scientist specializing in computer graphics, vision, and HCI. I completed my PhD at MIT in 2016, where I was advised by Fredo Durand, and am now a postdoctoral researcher at Stanford University working with Maneesh Agrawala.

A list of my publications can be found under the Publications Page.

Select Research Highlight Videos

I work on a range of topics in graphics, vision, and HCI, with most of my research focusing on how to apply work in these fields to new problems and application spaces. Below you will find a sampling of videos that describe different projects I've worked on. For a longer list of my publications, see my publications page or CV. My TED 2015 talk is also a good introduction to my work on visual vibration analysis.

Click on the thumbnails below to see videos summarizing different research projects. More can be found on my publications page.

Research Highlight

Speaking at TED 2015

Research Highlight

Visual Rhythm and Beat


Research Highlight

Interactive Dynamic Video

SIGGRAPH Asia 2015

Research Highlight

Computational Video Editing


Research Highlight

Visual Microphone


Research Highlight

Computational Bounce Flash

SIGGRAPH Asia 2016

Research Highlight

Visual Vibrometry

CVPR 2015 & PAMI 2016


Winter 2019

  • Check out the Wired article discussing some of our work on computational video editing.
  • I will be serving on the papers committee for SIGGRAPH Asia 2019.

Summer 2018:

Visual Rhythm & Beat Results

Below you will find a sampling of results from our SIGGRAPH 2018 paper on Visual Rhythm and Beat.

[Project Page]


We present a visual analogue for musical rhythm derived from an analysis of motion in video, and show that alignment of visual rhythm with its musical counterpart results in the appearance of dance. Central to our work is the concept of visual beats — patterns of motion that can be shifted in time to control visual rhythm. By warping visual beats into alignment with musical beats, we can create or manipulate the appearance of dance in video. Using this approach we demonstrate a variety of retargeting applications that control musical synchronization of audio and video: we can change what song performers are dancing to, warp irregular motion into alignment with music so that it appears to be dancing, or search collections of video for moments of accidentally dance-like motion that can be used to synthesize musical performances.
Visual Beat Result

Visual Rhythm And Beat (Overview Video)

A video giving an overview of the project and what we can do.

Visual Beat Result

Spot The Dancing Robot

Remix of Spot The Dancing Robot from Boston Dynamics.

Visual Beat Result

Psy's Best Friend

This example was a lot of fun to create. I found this Youtube channel for Dancing Nathan – a dog that does this strange flailing trick on a chair, which kind of looks like off-beat dancing.

Visual Beat Result

Kitty Shake Shake It

Cats dancing. Enough Said.

Visual Beat Result

If you're happy and you know it

The owners of the coffee shop I regular have a todler who is often watching this show when I go to get my coffee. They also like rap music, so I made this.

Visual Beat Result

Barney Don't Need No Education

Barney and Friends retimed to “Another Brick in the Wall” by Pink Floyd.