Paolo Cignoni

Computing Is Indeed a Discipline in Crisis

While Silicon Valley is investing tens of billions of dollars chasing the AGI dream, academic computing research in the U.S. is facing a severe drought.

cacm.acm.org/opinion/comp...

The position is fully funded for three years and will begin in November 2025. The main workplace will be in Pisa in my Lab.
For any questions, application support, or further details, feel free to contact me at: paolo.cignoni@cnr.it

We are pleased to announce an open PhD position at the CNR-ISTI
We are looking for a motivated PhD student with a background and interest in 3D Graphics, Geometry Processing, and Machine Learning.

**Deadline: 18 July 2025**

phd-ai-society.di.unipi.it/applications/
(pag 19 of the call: AI for 3D)

This letter has now reached almost 500 signatures, with many of my heroes, tool builders I have leaned on, professors who taught me, and others who made this field what it is.

If keeping this field accessible and egalitarian is important to you, add your signature in the link.

Signed. Definitely this is something that needs to be shared more...

Folks in the #SIGGRAPH community:

You may or may not be aware of the controversy around the next #SIGGRAPHAsia location, summarized here www.cs.toronto.edu/~jacobson/we...

If you're concerned consider signing this letter docs.google.com/document/d/1...
via this form
docs.google.com/forms/d/e/1F...

I signed and encourage colleagues to do the same.

Venue selection is fraught. Inevitably attendees will encounter visa issues, distance, expense, local politics, and other challenges. This venue, however, is simply unsafe for LGBTQ+ researchers, and the leadership's defensiveness is unacceptable.

Real Time, Accurate, Multi‐Featured Rendering of Bump Mapped Surfaces We present a new technique to render in real time objects which have part of their high frequency geometric detail encoded in bump maps. It is based on the quantization of normal-maps, and achieves e....

Great to see old (25y old!) tricks surfacing again!
doi.org/10.1111/1467...
Palette encoding of normals was a thing before shaders :) We run this stuff on a NVIDIA Riva 128 🤣

Various examples of color reconstruction on ancient statues

Please help us understand what experts expect from digital
reconstructions of ancient color!
We're running a short (10 min) anon survey for professionals in archaeology, art history, architecture, conservation/restoration, museums, and digital humanities.
👉 forms.gle/aEhYwGiveiNi...

Please Share!

Optimizing Free-Form Grid Shells with Reclaimed Elements under Inventory Constraints | Visual Computing Lab We propose a method for designing 3D architectural free-form surfaces, represented as grid shells with beams sourced from inventories of reclaimed elements from dismantled buildings. In inventory-cons...

More info on the project (code etc.)
vcg.isti.cnr.it/publication/...

Optimizing Free-Form Grid Shells with Reclaimed Elements under Inventory Constraints
Andrea Favilli, Francesco Laccone, Paolo Cignoni, Luigi Malomo, Daniela Giorgi
Computer Graphics Forum (Eurographics 2025)

Optimizing Free‐Form Grid Shells with Reclaimed Elements under Inventory Constraints We propose a method for designing 3D architectural free-form surfaces, represented as grid shells with beams sourced from inventories of reclaimed elements from dismantled buildings. In inventory-con...

We propose a computational framework for designing #freeform grid shells using reclaimed structural elements, explicitly addressing inventory constraints such as element lengths and availability without compromising design flexibility or structural integrity.
onlinelibrary.wiley.com/doi/10.1111/...

YouTube video by VisualComputingLaboratory Isti Optimizing Free-Form Grid Shells with Reclaimed Elements under Inventory Constraints (EG 2025)

Happy to share that our paper, "Optimizing Free-Form Grid Shells with Reclaimed Elements under Inventory Constraints", will be presented at #Eurographics 2025!
www.youtube.com/watch?v=L05g...

I had two NSF grants terminated last week, for a total of just under $1M. The largest one had just started and its goal was to provide users with more context and information on the content that they see on social media.

Defend the Internet Archive. Protect the Wayback Machine. Tell the music labels: Drop the 78s lawsuit. Sign our open letter on change.org

📢 The Internet Archive needs your help.

At a time when information is being rewritten or erased online, a $700 million lawsuit from major record labels threatens to destroy the Wayback Machine.

Tell the labels to drop the 78s lawsuit.

👉 Sign our open letter: www.change.org/p/defend-the...

🧵⬇️

Another viable solution for publishing "heavy" 3D models efficiently and simply on the web is the #3DHop framework that relies on the open source nexus multiresolution streaming 3D engine 3dhop.net
It handles hi-res 3D models (100Mtris) also on low-bandwidth, on plain web server.

TUM AI Lecture Series - The 3D Gaussian Splatting Adventure: Past, Present, Futur (George Drettakis) YouTube video by Matthias Niessner

TUM AI Lecture Series - The 3D Gaussian Splatting Adventure: Past, Present, Future www.youtube.com/live/DjOqkVI...

Final note, we also presented one incoming innovative tool for the 3D decomposition and analysis of the branches of corals. A cute mesh-processing problem mixing skeletonization, pruning, and clipping that will be integrated in MeshLab...

The effort for a research lab to maintain, improve and distribute an open source tool over the years is not small. But the sheer joy that you get when you see #TagLab widely used on the field in many reef monitoring projects is priceless.

Happy to report the success of our beloved #TagLab at #ReefFutures! Gaia Pavoni and Massimiliano Corsini are presenting the latest advances of our AI-powered, open-source segmentation tool for large ortho-images generated through the photogrammetric pipeline.

Vorogrid: A static-aware variable-density Voronoi mesh to design the tube structure tessellation of tall buildings | Visual Computing Lab In the context of tall building design, the tube concept represents one of the most performing systems. The diagrid is the widespread type of tube system and consists of a diagonal grid of beams that ...

And sometimes we are still working on this stuff...
vcg.isti.cnr.it/publication/...

Great post from the nervous systems guys!
Two small additional notes:
- Anisotropic CVD's beside being nice, are also quite interesting from a structural point of view vcg.isti.cnr.it/publication/...
- to actually generate nicer decompositions it is useful to add a further shape optimization step

Eric Haines posted on realtimerendering:

* GPU-Zen3 is out. We know that, but...
* Someone wrote a ray tracer in Minecraft. :)
* Someone ran Doom on E coli cells. =)

Yeah...

www.realtimerendering.com/blog/seven-t...

Indeed! Tetrahedral visibility sorting was not trivial (sorting centers of tetrahedra works only if the mesh is a Delaunay one and you sort the centers of circumsphere of the tetrahedra)

Definitely not a shame! It was stuff published on minor venues more than 25 years ago!

Curiosity, how the sorting for compositing is handled efficiently now? It was a real pain and was necessary for materials that are also emissive (needed for approximating scattering)...

I can't help but applaud something that reminds me of my PhD days! 😀
>25y ago I worked on the same ideas, definitely on different graphics hardware 😅

iris.cnr.it/bitstream/20...

BTW a open source implementation of the algorithm was already available inside MeshLab...

Texture Atlases before and after texture defragmentation

As a first post a happy note that the latest release of RealityCapture includes a reimplementation of our beloved Texture Defragmentation algorithm!
vcg.isti.cnr.it/publication/...

Is always gratifying to see that your solutions are actually useful and get adopted by industry in a short time...

Graphics Programming weekly - Issue 366 - November 17th, 2024 www.jendrikillner.com/post/graphic...

Graphics Programming weekly - Issue 365 - November 10th, 2024 www.jendrikillner.com/post/graphic...