PhD student @MIT @MediaLab @CameraCulture. Computer vision, computational imaging, and machine learning
Joined September 2016
- Tweets56
- Following185
- Followers196
- Likes458
Tzofi Klinghoffer retweeted
There is a new kind of robotics called "Vibe Robotics"
It's when you ask agents for fully functioning embodied agents (both hardware and software) that must solve a given task in physically grounded environments.
We build an evaluation to test how good agents (frontier models) are at "Vibe Robotics".
Website: artifactarena.ai/
Tzofi Klinghoffer retweeted
Excited to present two โจHighlight papers at #CVPR2026 this week!
DENALI: A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARs
๐nikhilbehari.com/denali/
Task-Driven Implicit Representations for Automated Design of LiDAR Systems
๐nikhilbehari.com/implicitlidโฆ
ALT CVPR 2026 Highlight Papers. DENALI: A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARs Task-Driven Implicit Representations for Automated Design of LiDAR Systems
Tzofi Klinghoffer retweeted
Iโm excited to share our Nature paper on seeing around corners with consumer LiDARs!
We show that consumer LiDAR sensors โ in your smartphones, AR headsets, self-driving cars, and robots โ can be used to see objects hidden around corners.
youtube.com/watch?v=N3LEhhQzโฆ
Tzofi Klinghoffer retweeted
๐๏ธ๐ Our new @ScienceAdvances paper: We replayed the Cambrian explosion of vision by evolving AI agents inside a physics engine to understand the principles that shape visual intelligence.
We believe that this is a promising way to do AI for science and build new forms of AI by computationally mimicking biological design principles of evolution and learning.
Website: eyes.mit.edu and paper links at the end of this thread ๐
Tzofi Klinghoffer retweeted
๐ธ Join us at ICCV 2025 for our workshop on Computer Vision with Single-Photon Cameras (CVSPC)!
๐๏ธย Sunday, Oct 19, AM โ PM at the Hawai'i Convention Center.
๐ Website: cvspc.cs.pdx.edu/.
๐ฃ๏ธ Invited Speakers: Mohit Gupta, @mpotoole, @Dongyu_Du, @DaveLindell, @adaveiitm.
๐Submit your poster and join the conversation! We welcome early ideas & in-progress work.
๐ Poster submission form: lnkd.in/gY5yMypc.
๐ Stay tuned for a CVSPC competition announcement!
๐ฅ Thanks to co-organizers: Atul Ingle, Mel White, Mian Wei and Sacha Jungerman!
@ICCVConference
Tzofi Klinghoffer retweeted
Excited to present our #CVPR2025 โจHighlight Paper "Blurred LiDAR for Sharper 3D."
We introduce a method for 3D Gaussian surfel reconstruction that combines RGB images with diffuse (blurred) LiDARs. Surprisingly, we find that these blurred LiDARs, often used as simple proximity sensors, can improve reconstruction quality over conventional mobile LiDARs for robust handheld scanning in challenging scenes.
๐ Come by Sunday, June 15 ยท ExHall D ยท Poster #77
๐ Website: nikhilbehari.github.io/bls3dโฆ
Tzofi Klinghoffer retweeted
This Wednesday (1-6PM, Room 106A) @CVPR we have a great lineup of keynote speakers, posters, and spotlights on neural fields and beyond: neural-bcc.github.io/
Have a question you want answered by a panel of experts in the field? Send it to us via: docs.google.com/forms/d/e/1Fโฆ
Tzofi Klinghoffer retweeted
๐ข I'm happy to share that I'll be joining @stonybrooku as an Assistant Professor in CS this Fall.
I will start the Photon Intelligence Lab, developing physics-aware AI that sees what we cannot โ by bridging optics, graphics, and vision.
Come join us! DM or meet me @ CVPR
๐งต๐
Tzofi Klinghoffer retweeted
Neural fields are showing huge promise for sensing far beyond just cameras โ if you're working at this intersection, this non-archival CVPR workshop is a great place to share your work and connect with others pushing the boundaries. Submit soon! ๐
neural-bcc.github.io
Only a couple weeks left to submit to Neural Fields Beyond Conventional Cameras at CVPR 2025! neural-bcc.github.io/
Our *non-archival* workshop welcomes both previously published and novel work. A great opportunity to get project feedback and connect with other researchers!
Tzofi Klinghoffer retweeted
Our 2013 SIGGRAPH paper "Femto-Photography: Capturing and Visualizing the Propagation of Light" has received the 2024 Test of Time Award! It's given to papers "that have had a significant and lasting impact on computer graphics and interactive techniques over at least a decade".
Tzofi Klinghoffer retweeted
MIT News covers our #CVPR2024 award-candidate paper PlatoNeRF ๐ congrats to @tklinghoffer!
news.mit.edu/2024/researcherโฆ
Check our oral && poster sessions on Thursday!
๐๏ธOral: Summit Flex Hall AB, 1:54-2:12pm
๐ฐPoster: Arch 4A-E Poster#2, 5:00-6:30 pm
Tzofi Klinghoffer retweeted
Super excited to be in Seattle this week for #CVPR2024 to present our recent work ๐๐ฎ๐ซ๐๐จ๐๐: ๐๐๐ง๐ฌ๐, ๐๐๐๐ฎ๐ซ๐๐ญ๐ ๐๐ง๐ ๐
๐๐ฌ๐ญ ๐๐ ๐๐ฒ ๐๐๐ฎ๐ซ๐๐ฅ ๐๐ง๐ฏ๐๐ซ๐ฌ๐ ๐๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐๐ ๐๐ข๐ ๐ก๐ญ.
Joint work with Maxx Wu, @ChenWenzheng, @DaveLindell, @kyroskutulakos
1/3
Tzofi Klinghoffer retweeted
Are you interested in neural fields and computational photography? Or just really like splines and have no one to talk to about splines? Come chat with me @CVPR2024 next week on our latest spliney neural fieldy burst photography project:
youtu.be/bvho-mtfAcI?si=fLp2โฆ
Tzofi Klinghoffer retweeted
Is it possible to reconstruct 3D geometry from measurements of a miniature time-of-flight proximity sensor? Yes! I'm excited to share our CVPR 2024 paper, "Towards 3D Vision with Low-Cost Single-Photon Cameras"
๐งตthread below
Tzofi Klinghoffer retweeted
๐ข๐ข๐ข A pulse of light takes ~3ns to pass through a Coke bottleโ100 million times less than it takes you to blink. Our work lets you fly around this 3D scene at the speed of light, revealing propagating wavefronts of light that are invisible to the naked eyeโfrom any viewpoint!
Flying with Photons: Rendering Novel Views of Propagating Light
๐ Website: anaghmalik.com/FlyingWithPhoโฆ
โจ๏ธ Code: github.com/anaghmalik/Flyingโฆ
w/ @NoahJuravsky, @Po_lhr, @GordonWetzstein, @kyroskutulakos and @DaveLindell
Tzofi Klinghoffer retweeted
Meta announces PlatoNeRF
3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar
paper page: huggingface.co/papers/2312.1โฆ
propose PlatoNeRF: a method to recover scene geometry from a single view using two-bounce signals captured by a single-photon lidar
Tzofi Klinghoffer retweeted
PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar
Tzofi Klinghoffer, Xiaoyu Xiang, Siddharth Somasundaram, Yuchen Fan, @c_richardt, @raskarmit, Rakesh Ranjan
tl;dr: NeRF->single-view two-bounce lidar time of flight->3D scene
arxiv.org/pdf/2312.14239.pdf
