Fabio Pellacini (@xelatihy) 's Twitter Profile
Fabio Pellacini

@xelatihy

CS Professor at University of Modena and Reggio Emilia. Computer Graphics and systems. Coder by heart, loves simplicity and pixels.

ID: 390754416

linkhttps://xelatihy.github.io calendar_today14-10-2011 14:10:33

1,1K Tweet

994 Followers

113 Following

UW Reality Lab (@uwrealitylab) 's Twitter Profile Photo

Teaching #ComputerGraphics via cartoon videos: Prof. Steve Seitz was inspired by #SchoolHouseRock and wondered if he could teach Intro to Computer Graphics that way at University of Washington. realitylab.uw.edu/staging/?p=850 #UWAllen #cartoonshort

Teaching #ComputerGraphics via cartoon videos: Prof. Steve Seitz was inspired by #SchoolHouseRock and wondered if he could teach Intro to Computer Graphics that way at University of Washington.
realitylab.uw.edu/staging/?p=850
#UWAllen #cartoonshort
Miro Knejp (@mknejp) 's Twitter Profile Photo

C++ developers: I will write a library so that others can reuse my code and don't have to re-invent the wheel. Also C++ developers: my library will have zero dependencies and I will rewrite everything from scratch.

Fabio Pellacini (@xelatihy) 's Twitter Profile Photo

Rust twitter: any idea why we have move as the default while immutable borrow needs to be specified? It seems to me that I most often call functions by immutable borrow and very rarely by move. In code, this add lots of '&' annotation for free functions. What am I missing?

Yann LeCun (@ylecun) 's Twitter Profile Photo

Hotter take: ML would have advanced faster if another front-end language had been available and widely adopted instead of Python. One that is interactive yet fast & compilable, multithreaded (no GIL), isn't bloated, doesn't care about white spaces,... E.g. Julia or some Lisp.

Yann LeCun (@ylecun) 's Twitter Profile Photo

Even hotter take: the fact that ML and Computer Vision researchers were largely using Matlab *held back progress for years*, mostly because implementing something like a ConvNet in 2005 Matlab would have been a total nightmare.

Claudio Mancinelli (@claudiomancine4) 's Twitter Profile Photo

Happy to announce that our paper "Computing the Riemannian center of mass on meshes" has been accepted to GMP 2023 and is avalibale online at authors.elsevier.com/a/1g%7EEkcAOr6…. This is a joint work with @Enrico_Puppo. See you at IGS'23 in Genova!

Happy to announce that our paper "Computing the Riemannian center of mass on meshes" has been accepted to GMP 2023 and is avalibale online at authors.elsevier.com/a/1g%7EEkcAOr6…. This is a joint work with @Enrico_Puppo.  See you at IGS'23 in Genova!
Aaron Lefohn (@aaronlefohn) 's Twitter Profile Photo

We finally get to share our neural materials research. We created custom highly-realistic reference materials, we invented new neural models, and we built new graphics systems. End result is these neural materials run in a real-time path tracer. research.nvidia.com/labs/rtr/neura…

We finally get to share our neural materials research.

We created custom highly-realistic reference materials, we invented new neural models, and we built new graphics systems. 

End result is these neural materials run in a real-time path tracer.

research.nvidia.com/labs/rtr/neura…
Tzu-Mao Li (@tzumaoli) 's Twitter Profile Photo

Sometimes I feel that the discrepancy is caused by cultural differences in graphics and CV/ML. Graphics research values "novelty" in both methodology and problem setting. Vision/ML has more of a SOTA seeking mindset, which granted has led to the crazy progress in the last decade

Fabio Pellacini (@xelatihy) 's Twitter Profile Photo

Graphics twitter: what is a good mastodon server for our community? And more importantly, is there a strong graphics community on mastodon?

Fabio Pellacini (@xelatihy) 's Twitter Profile Photo

AI twitter: I have been asked to teach a 4-8 hours lab on AI to 4th graders. Never done this my self. Does anybody have ideas or even better some materials on how to do this? Alfredo Canziani?