iiinova — where your digital self keeps evolving

Reposted by Wilhem Barbier

pltc @pltc.bsky.social · 16/07/2026

Packing my bag for #SIGGRAPH2026! @brunolevy01.bsky.social and I will be presenting our course on Optimal Transport for Fluid Simulation on Sunday July 19, 9am-12:15pm, Room 408B! Come say hi if you're around!

0254

Reposted by Wilhem Barbier

Baptiste GENEST @baptiste-genest.bsky.social · 27/05/2026

When dealing with noisy and/or partial inputs to describe a shape, the standard approach in geometry processing is to reconstruct a clean implicit surface first, and to do geometry on it. But why this one in particular? What about all the other surfaces that would have been coherent with the input?

12813

Wilhem Barbier @wbrbr.bsky.social · 21/01/2026

C'est curieux je ne savais pas, est-ce qu'il s'agit de MCF / PR qui font la transition ? Ou plutôt de chercheurs dans le privé ?

100

Reposted by Wilhem Barbier

Baptiste GENEST @baptiste-genest.bsky.social · 15/12/2025

Super happy and honored to share that our paper "BSP-OT: Sparse transport plans between discrete measures in log-linear time" won a *Best paper award* at SIGGRAPH Asia 2025! If you are here, come see my presentation about this work Wednesday afternoon! Many thanks to the award committee!

33210

Wilhem Barbier @wbrbr.bsky.social · 21/10/2025

Have you considered Alembic? I'd be curious to know if/why you discarded it, as sharing dynamic meshes is its core use-case, and it is supported in most 3D programs AFAIK. It serves a different purpose than OpenUSD, tailored towards "baked" representations rather than "editable".

100

Reposted by Wilhem Barbier

Baptiste GENEST @baptiste-genest.bsky.social · 01/10/2025

Computing the exact bijection of the optimal transport (OT) problem between very large point sets is completely untractable… In our SIGGRAPH Asia 2025 paper: “BSP-OT: Sparse transport plans between discrete measures in log-linear time” we get one with typically 1% of error in a few seconds on CPU!

14516

Reposted by Wilhem Barbier

Bruno Levy @brunolevy01.bsky.social · 18/09/2025

RING meeting in Nancy, Cyprien Plateau--Holleville presented presented his awesome work on exact integration of the differential quantities involved in Partial Optimal Transport. And that's not all: It comes with a combined physsim - Optimal Transport - rendering on the GPU !

Cyprien Plateau--Holleville in front of his title slide at the RING meeting

1135

Reposted by Wilhem Barbier

Marzia Riso @marziarice.bsky.social · 18/08/2025

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! 🎉

0172

Reposted by Wilhem Barbier

Axel Paris @axelparis.bsky.social · 18/08/2025

🚀The code for Lipschitz Pruning is now online thanks to @wbrbr.bsky.social🚀 🔗 github.com/wbrbr/Lipsch... It's a simple Vulkan app useful for experiments. Also, the monument done by @elie-michel.bsky.social is released under a CC-BY license📄 (poke @mattkeeter.com I remember you asked!)

Sample image from the Lipschitz pruning released application

12210

Reposted by Wilhem Barbier

Hugo Schott @hugoschott.bsky.social · 14/08/2025

Presenting this paper tomorrow morning at 9:30am, during the Lightning Fast Geometry session⚡ Come check it out if you can!

0507

Wilhem Barbier @wbrbr.bsky.social · 11/08/2025

I will be presenting the paper "Lipschitz Pruning: Hierarchical Simplification of Primitive-Based SDFs" at SIGGRAPH 2025 during the Best of Eurographics session! Come to my talk on Wednesday morning wbrbr.org/publications...

wbrbr.org

Lipschitz Pruning: Hierarchical Simplification of Primitive-Based SDFs

043

Reposted by Wilhem Barbier

Axel Paris @axelparis.bsky.social · 05/08/2025

📜 New SIGGRAPH 2025 paper 🎉 ❔How to compute bounding volumes for procedural Signed Distance Fields (SDFs)? This is not so trivial! 💡We propose a simple method called Sphere Carving. It extracts (convex) bounding volumes around SDFs, requires very few evaluations, and is GPU compatible.

12711

Wilhem Barbier @wbrbr.bsky.social · 24/06/2025

Thanks, I'm glad you liked it!

010

Wilhem Barbier @wbrbr.bsky.social · 23/06/2025

As a result, our method consistently reduces the build time although this comes at the cost of an increase in tracing time. We show that this tradeoff is worth it for real-time raytracing of complex dynamic scenes since rebuilds are particularly expensive. Check out the paper for more details!

130

Wilhem Barbier @wbrbr.bsky.social · 23/06/2025

In this paper we focus on maximizing build speed by removing this additional traversal. To do so we introduce a bottom-up collapsing algorithm, which we integrate into an existing high-performance BVH2 builder to obtain a fast wide BVH construction algorithm.

110

Wilhem Barbier @wbrbr.bsky.social · 23/06/2025

However most of the GPU BVH construction litterature focuses on binary hierarchies. A notable exception is H-PLOC by Benthin et al which uses a binary builder and a separate top-down collapsing step to convert the binary BVH into a wide BVH.

110

Wilhem Barbier @wbrbr.bsky.social · 23/06/2025

The standard acceleration structure for ray-tracing is the wide BVH, and fast GPU construction of these hierarchies is a key challenge for realtime raytracing. This is especially important for complex dynamic scenes where BVH rebuilds are a major bottleneck. Example: Flooded Sponza by Intel.

120

Wilhem Barbier @wbrbr.bsky.social · 23/06/2025

I am glad to attend #HPG2025 where I just presented our paper "Fused Collapsing for Wide BVH Construction", co-authored with Mathias Paulin. We propose a fast build algorithm for wide BVHs that directly computes a wide hierarchy without additional collapsing pass. Webpage: wbrbr.org/publications...

wbrbr.org

Fused Collapsing for Wide BVH Construction

14312

Wilhem Barbier @wbrbr.bsky.social · 03/06/2025

How do you get AABBs for the skinned clusters without transforming all the geometry? As the AABB also needs to bound the finer LODs this doesn't seem trivial. And transforming the bounding box is not conservative as the cluster weights vary. Would love to have more details on your solution for this!

100

Wilhem Barbier @wbrbr.bsky.social · 30/05/2025

Back to fiddling with my Vulkan path tracer

040

Wilhem Barbier @wbrbr.bsky.social · 14/05/2025

Thanks! Glad you like it, your paper was a big inspiration for this project.

010

Reposted by Wilhem Barbier

Baptiste GENEST @baptiste-genest.bsky.social · 10/05/2025

Implicit surfaces are great, but if you are not Inigo Quilez, it's really hard to control how they look... That's why I'm really proud to annonce our Eurographics 2025 paper: "Implicit UVs: Real-time semi-global parameterization of implicit surfaces".

45715

Wilhem Barbier @wbrbr.bsky.social · 07/05/2025

These pruned trees enable efficient evaluation of the SDF for rendering or discretization, resulting in >100x speedups for complex scenes compared to brute-force evaluation. Come to my talk next week for more details, or read the paper here: wbrbr.org/publications...

0136

Wilhem Barbier @wbrbr.bsky.social · 07/05/2025

Our algorithm takes as input an analytical SDF represented as a tree of smooth booleans and a 3D region of space, and computes a much smaller pruned tree equivalent within the region. This procedure is simple and efficient, using the Lipschitz prop. of the SDFs instead of costly interval arithmetic

Overview of our method. Left: a shape is described by a smooth CSG tree. Middle: the scene is divided into a grid, and we computed a pruned tree for every cell. Right: these pruned tree are much smaller than the input tree, and enable faster SDF evaluation for sphere tracing or SDF discretization.

140

Wilhem Barbier @wbrbr.bsky.social · 07/05/2025

I am proud to announce our Eurographics 2025 paper "Lipschitz Pruning: Hierarchical Simplification of Primitive-Based SDFs"! With Mathieu Sanchez (joint first author), @axelparis.bluesky.social, @elie-michel.bsky.social, Thibaud Lambert, @tamyboubekeur.bsky.social, Mathias Paulin and Théo Thonat.

Left: an input CSG tree and a much smaller pruned tree computed using our method.
Right: a rendered scene showing the number of active nodes per cell. Our method reduces the active nodes to less than 20 from the initial 6023 nodes of the input tree.

24618

Wilhem Barbier @wbrbr.bsky.social · 24/03/2025

Genuine question, why do you want to use Nanite if not for the performance ? With fully dynamic runtime procgen you can't escape the O(n) rendering cost which is the whole point of the Nanite LoD system IMO. Or is it the software rasterizer that you'd like to use with your geometry ?

100

Wilhem Barbier @wbrbr.bsky.social · 22/03/2025

Is this for CPU ray-tracing ? In my experience for GPU ray-tracing compressed wide BVHs do perform better (see CWBVH paper).

200

Wilhem Barbier @wbrbr.bsky.social · 28/01/2025

Are there any talks about their engine that you'd recommend (free or vaulted) ? I haven't heard much about it so I'm interested.

100

Wilhem Barbier @wbrbr.bsky.social · 29/12/2024

What are these characteristics ? Too axis-aligned ?

000

Wilhem Barbier @wbrbr.bsky.social · 16/12/2024

Love the color scheme! What's your setup ? (this doesn't look like a standard Windows+Visual Studio)

200

Wilhem Barbier @wbrbr.bsky.social · 13/12/2024

Is there a difference between an R-Tree and a BVH ? When (briefly) I looked into R-Trees they looked like the exact same thing, from a separate community

100

Wilhem Barbier @wbrbr.bsky.social · 10/12/2024

Better in what sense ? Better for innovation (no opaque acceleration structure) ? Better for the end users (no feature kept behind expensive HW) ? Or better for actual performance ?

100

Wilhem Barbier @wbrbr.bsky.social · 10/12/2024

That's interesting, as there is a (pretty old) dynamic scene benchmark which features an exploding Stanford dragon: gamma.cs.unc.edu/DYNAMICB/ I wonder if this usage clause was there at the time.

gamma.cs.unc.edu

UNC Dynamic Scene Benchmarks

020

Wilhem Barbier @wbrbr.bsky.social · 24/11/2024

Just spent hours trying to understand why a traceRayEXT() GLSL call wasn't working (no validation message), turns out I had set maxPipelineRecursionDepth to 0 instead of 1 for the RT pipeline.... Vulkan debugging is quite painful when the validation layers aren't catching your stupid mistakes ^^

030

Wilhem Barbier @wbrbr.bsky.social · 18/11/2024

I absolutely love your renders

000

Wilhem Barbier @wbrbr.bsky.social · 17/11/2024

This is far out of my area of expertise, but it seems like the multiresolution hash grid datastructure that was created for efficient NerF inference might be useful in your context. nvlabs.github.io/instant-ngp/ Your problem seems related to NerF except you learn visibility instead of radiance