Peter Michael (@gfxptr) header
Peter Michael (@gfxptr) profile picture

Peter Michael

@gfxptr

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

 Ithaca, NY
ptrmcl.github.io
Joined December 2021
  • Tweets78
  • Following286
  • Followers155
1Media
Photo by Peter Michael (@gfxptr)
Peter Michael retweeted
Abe Davis (@AbeDavis) profile picture
Abe Davis@AbeDavis16h
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!
Peter Michael (@gfxptr) profile picturePeter Michael@gfxptrNov 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.
1
10
502
Peter Michael retweeted
Yunyi Zhu (@yunyizhu_) profile picture
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!
1
1
1
20
2,042
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…
Hiding secret codes in light protects against fake videos | Cornell Chronicle

Hiding secret codes in light protects against fake videos | Cornell Chronicle

A team of Cornell computer science researchers has developed a way to “watermark” light in videos, which they can use to detect if video is fake or has been manipulated, another potential tool in the...

news.cornell.edu
1
4
328
Peter Michael retweeted
Jon Barron (@jon_barron) profile picture
Jon Barron
@jon_barron27 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…
Hamming, "You and Your Research" (June 6, 1995)

Hamming, "You and Your Research" (June 6, 1995)

Intro: I have given a talk with this title many times, and it turns...

youtube.com
6
53
1
357
46,105
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…
OmniMotion allows for better video motion estimation | Cornell Chronicle

OmniMotion allows for better video motion estimation | Cornell Chronicle

Cornell researchers have developed an optimization tool, OmniMotion, to estimate motion throughout an input video, which has potential applications in video editing and generative AI video creation....

news.cornell.edu
2
6
1,002
Peter Michael retweeted
AK (@_akhaliq) profile picture
AK
@_akhaliq27 Apr 2023
Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image Generation abs: arxiv.org/abs/2304.13681 project page: ray-cond.github.io/
Image from AK (@_akhaliq)
1
43
6
193
56,480
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: bit.ly/3tDxHMa
1
5
At today's @ImageUCPH workshop, section head @KErleben asked me to speak about "how to get cool research ideas." (1/25)
1
57
10
265
Peter Michael retweeted
Alex Dimakis (@AlexGDimakis) profile picture
Alex Dimakis
@AlexGDimakis18 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.
5
7
160
Peter Michael retweeted
François Chollet (@fchollet) profile picture
François Chollet
@fchollet7 Sep 2022
I'll tell you a secret about having more impact. You've got to focus on fewer things, ideally just one -- your most ambitious idea. And you've got to commit and finish it.
44
372
37
2,606
📢📢📢 Thrilled to introduce "𝐌𝐨𝐛𝐢𝐥𝐞𝐍𝐞𝐑𝐅: exploiting the polygon rasterization pipeline for efficient neural field rendering on mobile architectures" → with 𝐥𝐢𝐯𝐞 𝐝𝐞𝐦𝐨𝐬 arxiv.org/abs/2208.00277 (Internship project lead by @ZhiqinChen3)
7
374
53
2,172
Peter Michael retweeted
Patrick Esser (@pess_r) profile picture
Patrick Esser
@pess_r23 Jun 2022
We present Latent Diffusion Models in tomorrow's Image & Video Synthesis and Generation session @CVPR in Hall B1 (Thur. 08:30-10:18). Join us for a chat at Poster #7 between 10:00-12:30 in Hall B2-C and sample some jazz! With @robrombach @andi_blatt D. Lorenz @runwayml B. Ommer
4
35
2
359
Peter Michael retweeted
Chung-Yi Weng (@chungyiTW) profile picture
Chung-Yi Weng@chungyiTW8 Jun 2022
Feel pleased to show off our upcoming @CVPR paper, HumanNeRF. Our method turns a Youtube video of moving people into a free-viewpoint video! Page: grail.cs.washington.edu/proj… Video: youtu.be/GM-RoZEymmw with Brian Curless, @_pratul_, @jon_barron, @kemelmi More in thread! (1/7)
11
186
32
873
Peter Michael retweeted
Jeff Dean (@JeffDean) profile picture
Jeff Dean
@JeffDean24 May 2022
AI can unlock joint human/computer creativity! Imagen is one direction we are pursuing: gweb-research-imagen.appspot… "A high contrast portrait of a very happy fuzzy panda dressed as a chef in a high end kitchen making dough. There is a painting of flowers on the wall behind him."
Image from Jeff Dean (@JeffDean)
45
268
88
1,549
Automate the tedious. Focus on creativity. Incredible @runwayml research collab with between @pess_r @SenguptRoni @gfxptr @uwcse
Image from Cristóbal Valenzuela (@c_valenzuelab)
AK (@_akhaliq) profile pictureAK
@_akhaliq20 May 2022
Towards Unified Keyframe Propagation Models abs: arxiv.org/abs/2205.09731 github: github.com/runwayml/guided-i…
3
28
Peter Michael retweeted
Runway (@runwayml) profile picture
Runway
@runwayml21 Apr 2022
Collaborative video editing is here! 👨‍👨‍👦‍👦 Real-time multiplayer editing 🔗 Invite collaborators with a single link 🌍 Make projects public 🏢 Create Teams (early beta coming soon!) Start collaborating now: runwayml.com
3
30
19
175
Very exciting 'breaking' news! CompVis (research group behind VQGAN) have just released a new 1.45B parameter model to its Latent Diffusion model: github.com/CompVis/latent-di… From the released image it seems like it has an unprecedented text-synthesis capacity. More to follow soon
Image from apolinario (poli) (@multimodalart)
12
113
17
584
Peter Michael retweeted
Runway (@runwayml) profile picture
Runway
@runwayml30 Mar 2022
Ever wondered what it's like to work at Runway? Check out today's blog post for a peek into the interview process and day to day of our interns Sharon Lee and @gfxptr: bit.ly/3iTL7xW And yes — we're hiring!
Image from Runway (@runwayml)
1
6
1
12
Failure is the dance partner of success. It can feel insurmountable at times. Here is my story of academic failures -- my anti-CV if you will. I hope people find it useful. perceiving-systems.blog/en/n…
The Road to Success is Paved with Rejection Letters

The Road to Success is Paved with Rejection Letters

perceiving-systems.blog
30
209
26
934
Peter Michael retweeted
Runway (@runwayml) profile picture
Runway
@runwayml16 Feb 2022
We had the opportunity to chat with Meta @RealityLabs Research Scientist @jbhuang0604 for our latest Creative AI Conversation. Jia-Bin shares a bit about his background, and expertise in Computational Photography. Full interview here: youtu.be/CuU8N7gonn8
2
2
10
Load more