Every lens leaves a blur signature—a hidden fingerprint in every photo.
In our new #TPAMI paper, we show how to learn it fast (5 mins of capture!) with Lens Blur Fields ✨
With it, we can tell apart ‘identical’ phones by their optics, deblur images, and render realistic blurs.
09.09.2025 22:48 — 👍 150 🔁 49 💬 3 📌 9
Predicting manufacturing costs directly from 2D CAD drawings using XGBoost on geometric features
22.08.2025 22:07 — 👍 6 🔁 1 💬 1 📌 0
Yeah document parsing is cool, but what about CAD drawing parsing... (but with documents too 🥺)
20.08.2025 19:23 — 👍 4 🔁 0 💬 0 📌 0
Just added three.js to our landing page
15.08.2025 02:16 — 👍 4 🔁 0 💬 0 📌 0
Thanks for sharing, Sung!!
11.01.2025 19:33 — 👍 1 🔁 0 💬 0 📌 0
@yongyuanxi.bsky.social open-sourced research-oriented portfolio website template in Next.js and React- where you can update everything just by editing TypeScript objects and looks good on mobile.
Template: github.com/tovacinni/re...
Demo: tovacinni.github.io/research-web...
11.01.2025 18:20 — 👍 18 🔁 2 💬 1 📌 0
Picture of a stage at SIGGRAPH Asia, where we receive the Honorable Mention Award
🏆 So honored that our paper received the Honorable Mention #Award at #SIGGRAPHAsia!
I really like this paper BTW, it is about procedural #SignedDistanceFields, a simple idea to #differentiate them and thus provide #DirectManipulation ✨
More in the🧵⤵️ 1/8
03.12.2024 08:33 — 👍 38 🔁 8 💬 1 📌 1
lol def dont disagree with that- these days uv makes things a little better though (but still a nightmare once you have cuda extensions etc)
23.11.2024 09:07 — 👍 1 🔁 0 💬 0 📌 0
Added!
23.11.2024 03:56 — 👍 1 🔁 0 💬 1 📌 0
added!
23.11.2024 03:56 — 👍 0 🔁 0 💬 0 📌 0
Definitely agree wrt race conditions! Rust makes concurrency actually fun the work with
22.11.2024 22:35 — 👍 0 🔁 0 💬 0 📌 0
Note the “for C++-like systems programming”. Python is not a language meant for that.
22.11.2024 22:34 — 👍 0 🔁 0 💬 1 📌 0
Would love to be added :D
research.nvidia.com/labs/dir/mag...
22.11.2024 00:49 — 👍 0 🔁 0 💬 0 📌 0
Would love to be on there as well 😃
21.11.2024 16:35 — 👍 1 🔁 0 💬 0 📌 0
👋 working on high throughput LLMs for data enrichment
21.11.2024 15:38 — 👍 1 🔁 0 💬 0 📌 0
You can definitely replace the kernel launch code with Rust / PyO3 (although I’ve never tried this myself) but the kernels themselves will still be in CUDA C++ (just runtime or compile time built by Rust)
21.11.2024 15:23 — 👍 2 🔁 0 💬 0 📌 0
Yep cudarc! (didn't exist the last time I considered learning Rust which was a long time ago)
21.11.2024 14:40 — 👍 3 🔁 0 💬 1 📌 0
(Hopefully I'll never have to find out)
21.11.2024 14:32 — 👍 1 🔁 0 💬 0 📌 0
To be fair maybe CMake wouldn't be so bad now with Claude
21.11.2024 14:32 — 👍 3 🔁 0 💬 2 📌 0
I've definitely wasted many hours of my life fighting CMake 😆
21.11.2024 14:32 — 👍 1 🔁 0 💬 0 📌 0
Yes the functional features are definitely very nice too! The status quo on teams I've worked on has generally unfortunately just been CMake 😭
21.11.2024 14:31 — 👍 3 🔁 0 💬 0 📌 0
CUDA support in Rust is pretty good these days which was also a reason why Rust was easier to adopt now! (but of course muddles the whole 'memory safety' thing which is also why I don't think that's the main feature of Rust)
21.11.2024 14:27 — 👍 5 🔁 0 💬 1 📌 0
Haven't built a sim engine with Rust, but specifically for concurrency code Rust feels way less scary than C++. So application might matter a bit.
Also it definitely would've taken longer for me to learn Rust if I didn't also have Claude to explain all the concepts / compiler errors for me!
21.11.2024 14:22 — 👍 1 🔁 0 💬 1 📌 0
Many think Rust is primarily about memory safety, but the real reason to use Rust is developer productivity (for C++-like system programming) from having a sane package manager and type system.
21.11.2024 12:30 — 👍 470 🔁 25 💬 32 📌 5
"MIT of the North" as they say 🤣
21.11.2024 07:09 — 👍 1 🔁 0 💬 0 📌 0
A year ago if I asked these LLMs about me it would have no idea. Still not entirely correct but scary it can hold this very obscure knowledge…
19.11.2024 07:50 — 👍 7 🔁 0 💬 2 📌 0
Yeah here's my geometry processing starter pack. I hand-picked researchers and practitioners either in geometry processing or not, and some people are definitely missing so,
go.bsky.app/Dqw66qn
18.11.2024 17:59 — 👍 53 🔁 18 💬 7 📌 1
Done!
19.11.2024 07:41 — 👍 1 🔁 0 💬 0 📌 0
🔧 Researcher in Machine Assisted Theorem Proving at https://centaur.stanford.edu/
☯️ Director of NorCal Hakkero Factory No. 1 (I make #touhou cosplay props)
🔗 https://leni.sh, https://pixelfed.social/chrysoberyl
❄️ Training AI on my content is prohibited
Asst. Prof. in Machine Learning at UofT. #LongCOVID patient.
https://www.cs.toronto.edu/~cmaddis/
Postdoc at Imperial College London
Interested in SLAM and multi-device optimisation
https://rmurai.co.uk
Research Scientist at #Adobe. PhD in Computer Graphics. Author of #LearnWebGPU C++. Creative Coding. Indie game. VFX. Opinions are my own. Writes in 🇫🇷 🇺🇸.
https://portfolio.exppad.com
https://twitter.com/exppad
postdoc @MIT | phd @UCSanDiego | ce alum @UWaterloo | i mostly tweet on gfx, games, or movies | ex-pixar/weta/ubisoft/activision/treyarch/sidefx🎮👨💻👨🏫 🇨🇦🇮🇷
PhD student at University of Toronto, Research Intern at Waabi, ex. Google DeepMind, 3D Vision Enthusiast
Senior Research Scientist @ NVIDIA
(Lead: https://github.com/NVlabs/DoRA)
Ph.D. @ Georgia Tech | Multimodal AI
https://minhungchen.netlify.app/
From SLAM to Spatial AI; Professor of Robot Vision, Imperial College London; Director of the Dyson Robotics Lab; Co-Founder of Slamcore. FREng, FRS.
Assistant Professor at UPenn. https://lingjie0206.github.io. Research interests: Neural Scene Representation, Neural Rendering, 3D Reconstruction, Human Performance Modeling and Capture.
Assistant Professor of Computing Science at SFU. Ph.D. from @ucberkeleyofficial.bsky.social and Bachelor's from @uoft.bsky.social. Formerly at Google and Member of the IAS.
http://www.sfu.ca/~keli/
Research Scientist @Toyota Research Institute | Prev. PhD in AI, ML and CV @GeorgiaTech | Researching 3D Perception, Generative AI for Robotics and Multimodal AI
W: https://zubairirshad.com
Machine Learning Researcher @Apple MLR
Incoming Assistant Professor @Penn CIS
See more details https://jiataogu.me
http://bingxu.tech
Computer graphics, Light transport, Rendering, Painting. PhD candidate @UCSanDiego. Intern @NVIDIA; Sketches https://www.instagram.com/bing_xu_art
Computer Vision Researcher and Professor at University of Guelph: https://scholar.google.com/citations?user=Gnezf-4AAAAJ&hl=en
Head of Research @ Simular. Professor @ UC Santa Cruz. Working on #Multimodal #Embodied #AIAgents. AI for Humanity in the long run. he/him
📍Bay Area 🔗 https://eric-xw.github.io
PhD-ing at UMD. Knows a little about multimodal generative models. Check out my website to know more - https://somepago.github.io/
#CS Associate Prof York University, #ComputerVision Scientist Samsung #AI, VectorInst Faculty Affiliate, TPAMI AE, ELLIS4Europe Member, #CVPR2025 Publicity Chair on X
📍Toronto 🇨🇦 🔗 csprofkgd.github.io
🗓️ Joined Nov 2024