Publications
A (possibly not up to date) list of our publications.
LightShop: High-Precision Interactive Computational Light Painting
Accepted to UIST 2026 , more details coming soonPeter Michael, Andrew Arena, Harald Haraldsson, Abe Davis
More Details Coming Soon! (Conditionally Accepted)
Narrative Keyframing for Generative Creative Writing
Accepted to UIST 2026 , more details coming soonChao Zhang and Abe Davis
More Details Coming Soon! (Conditionally Accepted)
Micro-Edits: Computational Support for Fine-Scale Edits in Film
Accepted to UIST 2026 , more details coming soonNhan Tran, Hijung Valentina Shin, Abe Davis, Mackenzie Leake
More Details Coming Soon! (Conditionally Accepted)
Interactive Explainable Ranking
CHI 2026Chao Zhang and Abe Davis
CHI 2026 Best Paper Award
We use AI and optimization to help people make more consistent and explainable decisions. More specifically, we identify inconsistencies between a user's stated values and their observed preferences, and help them resolve or explain these inconsistencies. This work won Best Paper at CHI 2026!
CineCraft: Unified Shot Planning, Capture, and Post-Processing for Mobile Cinematography
CHI 2026Nhan Tran, Sam Belliveau, Zixin Xu, and Abe Davis
Mobile application that lets users storyboard complex cinematic shots, then uses the storyboard to automate precise camera control during real capture.
Noise-Coded Illumination For Forensic And Photometric Video Analysis
SIGGRAPH 2025 / ACM Transactions on Graphics (Journal Paper)Peter F. Michael, Zekun Hao, Serge Belongie, Abe Davis
We use coded noise to add an invisible watermark to lighting that helps detect fake or manipulated video.
Pocket Time-Lapse
SIGGRAPH 2025Eric M. Chen, Žiga Kovačič, Madhav Aggarwal, Abe Davis
Create panoramic time-lapse by taking photos during your regular daily routine. New methods for robust registration and rendering.
Try out our registration code, which makes it super easy to make your own unstructure time-lapse!
ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary
CVPR 2025
A 3D scene generation pipeline leveraging the power of LLMs and vision foundation models. Our method works on a diverse range of scene categories and aesthetic styles, and produces modular, editable results by representing each object as a 3D mesh.
How to Train Your Dragon: Automatic Diffusion-Based Rigging for Characters with Diverse Topologies
Eurographics 2025Zeqi Gu, Difan Liu, Timothy Langlois, Matthew Fisher, Abe Davis
Automatic example-based rigging and skinning of cartoon characters with arbitrary skeletal topologies! Oh my!
Visual Chirality
CVPR 2020 (Selected for Oral Presentation)Zhiqiu Lin, Jin Sun, Abe Davis, Noah Snavely
Nominated for Best Paper
How does reflection change what we learn from images? Despite widespread use in data augmentation, people had not looked closely at this question before our work.
Head-mounted Augmented Reality for Guided Surface Reflectance Capture
CVPR Workshop on Computer Vision for Augmented and Virtual RealityHarald Haraldsson, Søren Skovsen, Ser-Nam Lim, Steve Marschner, Serge Belongie, Abe Davis
Decoupled Localization and Sensing with HMD-based AR for Interactive Scene Acquisition
CVPR Workshop on Computer Vision for Augmented and Virtual RealitySøren Skovsen, Harald Haraldsson, Abe Davis, Henrik Karstoft, Serge Belongie
Modal Imaging of Portsmouth, New Hampshire Bridge for Video-Based Structural Health Monitoring
IWSHM 2019Abe Davis, Justin G. Chen, Abe Davis, Travis M. Adams, Hao Sun, Erin S. Bell, Fredo Durand, Oral Buyukozturk
Comparing modal images of a bridge with an FEM model of that bridge.
Structural Health Monitoring from the Window Seat of a Passenger Airplane
IWSHM 2017Abe Davis, Justin G. Chen, Oral Buyukozturk, Fredo Durand, Doug L. James
Winner, SHM In Action 2017
Monitoring the vibration modes of an airplane wing from the window seat using a mobile phone.
Computational Video Editing for Dialogue-Driven Scenes
SIGGRAPH 2017Mackenzie Leake, Abe Davis, Anh Truong and Maneesh Agrawala
Computational tools for fast, high-level, editing of multiple video takes for dialogue driven scenes.
Visual Vibrometry: Estimating Material Properties from Small Motions in Video
PAMI 2016Abe Davis*, Katherine L. Bouman*, Justin G. Chen, Michael Rubinstein, Oral Buyukozturk, Fredo Durand, William T. Freeman
Improving on our CVPR 2015 paper, we adding additional analysis, showed you could do damping estimation, and infer hidden structure (e.g., tell whether a container is leaking).
Smaller Than the Eye Can See: Vibration Analysis with Video Cameras
19th World Conference on Non-Destructive Testing 2016 (WCNDT)Oral Buyukozturk, Justin G. Chen, Neal Wadhwa, Abe Davis, Frédo Durand, and William T. Freeman
Including visual vibration analysis of earthquakes!
Visual Vibration Analysis
MIT EECS PhD ThesisAbe Davis
Winner of the MIT Sprowls thesis award
ACM SIGGRAPH Thesis Award, Honorable mention
My dissertation on visual vibration analysis and its applications.
"Image-Space Modal Bases for Plausible Manipulation of Objects in Video"
SIGGRAPH Asia 2015Abe Davis, Justin Chen, Fredo Durand
This paper describes an improved version of the demo I showed at the end of my TED 2015 talk (with some improvements since TED) and demonstrates applications related to low-cost special effects.
Video Camera-based Vibration Measurement for Condition Assessment of Civil Infrastructure
International Symposium Non-Destructive Testing in Civil EngineeringChen, J. G.; Davis, A.; Wadhwa, N.; Durand, F.; Freeman, W. T.; Buyukozturk, O.
More work with folks from the Civil Engineering department on NDT of structures using visual vibration analysis.
Long Distance Video Camera Measurements Of Structures
10th International Workshop on Structural Health Monitoring (IWSHM 2015)Justin G. Chen, Neal Wadhwa, Abe Davis, Fredo Durand, William T. Freeman, Oral Buyukozturk
Work with folks from the Civil Engineering department looking at how distance effects visual vibration analysis for NDT of structures. I presented this at IWSHM 2015.
Light Field Reconstruction Using Sparsity in the Continuous Fourier Domain
TOG / SIGGRAPH 2015Lixin Shi, Haitham Hassanieh, Abe Davis, Dina Katabi, Fredo Durand
1) We show that light fields are really only sparse in the continuous frequency domain,
and 2) We show how to leverage that sparsity in an optimization over continuous frequencies to reconstruct even highly non-Lambertian light fields.
The Visual Microphone: Passive Recovery of Sound from Video
SIGGRAPH 2014Abe Davis, Michael Rubinstein, Neal Wadhwa, Gautham J. Mysore, Fredo Durand, William T. Freeman
Discover Magazine Best Science Breakthroughs of 2014, #32
This project received a lot of press. Check out the project webpage for some examples. Also check out the Code.
Laser Speckle Photography for Surface Tampering Detection
IEEE Conference on Computer Vision and Pattern Recognition, (CVPR 2012)YiChang Shih, Abe Davis, Samuel W. Hasinoff, Fredo Durand, and William T. Freeman
Google Student Travel Award
Use lasers to detect tampering with a surface. We can detect whether someone has lightly touched a surface even if they were wearing gloves! This system also uses AR for ultra-precise rephotography.
