←
Peter Michael80 posts
Peter Michael avatar

Peter Michael

@gfxptr

Ph.D. Candidate @cornell_cs. Computational imaging. Prev @uwcse @runwayml

◷ Joined December 2021▧ 1 Photos and videos
thijs avatar
⟳ Peter Michael retweeted
thijs@cdngdev·Nov 16

i recreated THE ENTIRE WORLD in minecraft at 1:1 scale. every building on earth, including your house! to do this, i trained a SOTA world-to-minecraft generator on maps data, complete with furnished home interiors! play and check out your neighborhood: worldcraft.gg

0:36
Abe Davis avatar
⟳ Peter Michael retweeted
Abe Davis@AbeDavis·Nov 5

Come check out our work on LightShop, which will be presented by @gfxptr and Andrew Arena in the 11am session today at #UIST2026! We build an interactive tool for super high precision computational light painting!

Excited to share LightShop (UIST 2026)! We created an interactive, computational system that enables the creation of high-precision light paintings. What makes it really neat is that it combines light painting's physically accurate lighting with computational precision.

0:30
Yunyi Zhu avatar
⟳ Peter Michael retweeted
Yunyi Zhu@yunyizhu_·Nov 1

🔎 ShiftLens: new paper at #UIST2026 w/ @NargesPJ 3D-printed objects that change their look as you use them. Lenticular lenses shifting over printed patterns, with lenses, patterns & actuation mechanism auto-generated and 3D printed. Custom keychains printed at our demo!

0:30
Peter Michael avatar
Peter Michael@gfxptr·Nov 2

w/ Andrew Arena (amazing undergrad!), @haraldsson, and @AbeDavis. Our UIST talk is this Thursday at 11am in the "Light, Gaze, and Simulated Users" session. Swing by if you're around!

Peter Michael avatar
Peter Michael@gfxptr·Nov 2

Excited to share LightShop (UIST 2026)! We created an interactive, computational system that enables the creation of high-precision light paintings. What makes it really neat is that it combines light painting's physically accurate lighting with computational precision.

0:30
Peter Michael avatar
Peter Michael@gfxptr·11 Aug 2025

Come to our #SIGGRAPH2025 talk today at 2pm at the Computational Imaging, Lighting & Display session in the West Building rooms 118-120 to learn more!

Excited to share our ACM TOG/ SIGGRAPH '25 work on Noise-Coded Illumination (NCI)! We use coded noise to add an invisible watermark to lighting that helps detect fake or manipulated video. With @gfxptr and collaborators @zekun_hao and @SergeBelongie. url: peterfmichael.com/nci/

2:20
Cornell Chronicle avatar
⟳ Peter Michael retweeted
Cornell Chronicle@CornellNews·30 Jul 2025

Detecting a fake: A team of @CornellCIS researchers has developed a way to “watermark” light in videos to detect if video is fake or has been manipulated, another potential tool in the fight against #misinformation. @AbeDavis @SergeBelongie @siggraph news.cornell.edu/stories/202…

Jon Barron avatar
⟳ Peter Michael retweeted
Jon Barron@jon_barron·27 Oct 2023

If you have a career in research, or if you aspire to have a career in research, you must watch (or read) Dick Hamming's "You and Your Research". Easily the best advice out there on the subject. Video: youtube.com/watch?v=a1zDuOPk… Transcript: cs.virginia.edu/~robins/YouA…

Cornell Bowers Computing and Information Science avatar
⟳ Peter Michael retweeted
Cornell Bowers Computing and Information Science@Cornell_Bowers·12 Oct 2023

Noah Snavely @Jimantha, associate professor of computer science at @Cornell_Tech & @Cornell_CS, and a team of researchers have developed OmniMotion, a new video optimization tool that estimates motion across a full video with only a small sample of frames. news.cornell.edu/stories/202…

Cornell Computer Science avatar
⟳ Peter Michael retweeted
Cornell Computer Science@Cornell_CS·18 Nov 2022

An app developed by researchers in @AbeDavis’ group uses augmented reality to help users repeatedly capture images with a phone or tablet from the same location to make time-lapse videos. ReCapture is now available in the Apple app store. Read more: https://t.co/jkc4LlP524

0:08
Peter Michael avatar
Peter Michael@gfxptr·29 Sep 2022

wild.

AI at Meta@AIatMeta29 Sep 2022

We’re pleased to introduce Make-A-Video, our latest in #GenerativeAI research! With just a few words, this state-of-the-art AI system generates high-quality videos from text prompts. Have an idea you want to see? Reply w/ your prompt using #MetaAI and we’ll share more results.

0:05
Alex Dimakis avatar
⟳ Peter Michael retweeted
Alex Dimakis@AlexGDimakis·18 Sep 2022

Is there a doctor on the plane? -Yes, but not that kind of doctor. -The passenger in 36c is trying to inpaint an image using a pre-trained stable diffusion model and simply copy-pastes the inpainting observed part in place, after each iteration! -Ok, I got this.