Marzia Riso

Marzia Riso

@marziarice.bsky.social

Postdoctoral Researcher @ Inria Université Côte d’Azur

76 Followers 79 Following 8 Posts Joined Dec 2024
3 months ago
Post image Post image Post image

Another round, another conference!

At #STAG2025, I’ll show how to expand small hand-drawn patterns into arbitrarily large and perfectly tileable textures using diffusion models.

Check our paper “Structured Pattern Expansion with Diffusion Models” to learn more -> marzia-riso.github.io/pex.html

2 0 0 0
3 months ago
Post image Post image Post image

Curious about how decommissioned wind turbine blades can become domino-like modules for pump tracks? Check out our case study “From Blades to Tracks”, joint work with TU Delft | IDE presented at the 10th ACM Symposium on Computational Fabrication at MIT!

Webpage: www-sop.inria.fr/reves/Basili...

1 0 0 0
6 months ago
Post image Post image Post image

It was so good to be in Vancouver to present our work “Interactive Optimization of Scaffolded Procedural Patterns” at #Siggraph2025!

If you couldn’t make it, have a look at our project page!
💻 marzia-riso.github.io/iospp.html

Can’t wait for what’s next! 🎉

17 2 0 0
7 months ago

Join out talk on Thursday 14/08 in the "Packing In Structure" session at 3:45pm (West Building, Rooms 211–214) to see this in action!

0 0 0 0
7 months ago
Post image Post image

The gradient-free optimization enables fast optimization over both continuous and discrete parameters, while GPU-accelerated SDF evaluation keeps the optimization loop interactive. Together, they let us achieve real-time interaction even for complex, highly parameterized procedural patterns.

0 0 1 0
7 months ago
Post image Post image

Each new sketch triggers a gradient-free optimization process that minimizes a weighted per-pixel distance between the pattern’s SDF and the stroke SDF. The weights extracted from the both pattern and "Void" strokes enable focusing on drawn regions as well as empty ones.

0 0 1 0
7 months ago
Post image

We model a procedural pattern generator as a sequence of functions called Levels, where each Level’s parameters form a superset of the previous one
This enables coarse-to-fine optimization, where earlier parameters are inherited and new ones are optimized.

0 0 1 0
7 months ago
Post image

In our #SIGGRAPH2025 paper “Interactive Optimization of Scaffolded Procedural Patterns”, we introduce a new way to define and optimize procedural patterns in a sketch-based interactive design workflow.

14 4 1 0
1 year ago
Post image

SIGGRAPH Asia (still) coming up! Second paper thread!

"Direct Manipulation of Procedural Implicit Surfaces" where we explore how to create a WYSIWYG editing interface for procedural representations, avoiding awkward sliders!
eliemichel.github.io/SdfManipulat...

54 16 2 3
1 year ago
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

37 7 1 1