Dimitri Diakopoulos

Dimitri Diakopoulos

@ddiakopoulos.bsky.social

I make stuff sometimes! when i’m not blacksmithing, i shepard a research engineering team at apple

603 followers294 following26 posts

Dimitri Diakopoulos reposted

meshoptimizer 1.2 is out! Featuring support for tangent generation, a significantly faster vertex decoder for Intel/AMD CPUs, several new smaller algorithms (cluster position compression, triangle filtering, clusterlod BVH) and more. GitHub stars and boosts appreciated! github.com/zeux/meshopt...

Dimitri Diakopoulos reposted

Excited to share our new work at CVPR 2026: Learning Convex Decomposition via Feature Fields. We introduce the first feedforward openworld model that generates high-quality convex decompositions for any 3D shapes in seconds, enabling faster simulation. Project: research.nvidia.com/labs/sil/pro...

Dimitri Diakopoulos reposted

Adobe just released an Apache-2.0 licensed reference implementation of the OpenPBR Surface standard, extracted from their in-house Eclair renderer. Neat trick: the reference implementation cross-compiles for C++, GLSL, Cuda, Metal, and Slang! github.com/adobe/openpb...

github.comGitHub - adobe/openpbr-bsdf: Adobe's reference implementation of the OpenPBR BSDFAdobe's reference implementation of the OpenPBR BSDF - adobe/openpbr-bsdf

Dimitri Diakopoulos reposted

Tech Company: At long last, we have created the Torment Nexus from classic sci-fi novel Don't Create The Torment Nexus. FOSS nerds: the Torment Nexus cannot be ethical until it is Open Source

Dimitri Diakopoulos reposted

Hey All, I made a header only C++ library (MIT) where line of code inits, then you can start writing to pixels on the screen. I call it thirteen.h, inspired by the simplicity of the 13h days. Examples include a mandelbrot viewer and a playable mine sweeper game. github.com/Atrix256/Thi...

Dimitri Diakopoulos reposted

📣 NEW! I’ve just released the BIGGEST and perhaps most creative project I’ve ever worked on! “Searching for Birds” searchingforbirds.visualcinnamon.com 🐤 A project, an article, an exploration that dives into the data that connects humans with birds, by looking at how we search for birds.

Dimitri Diakopoulos reposted

Hey I made a new thing - it's called Gradientspace Graph, and it's a C#-based NodeGraph Programming system that also supports inline C# and Python "Code Nodes". The NodeGraph Engine is MIT Open-Source and the Editor is Free. More details here: www.gradientspace.com/tutorials/20...

gradientspace.comGradientspace Graph Beta — gradientspaceI have released an initial version of Gradientspace Graph (GSGraph), a new C#-based NodeGraph Programming environment that also supports inline text-coding in C# and Python (and LLM-based CodeNode gen...

Dimitri Diakopoulos reposted

Dimitri Diakopoulos reposted

Happy to announce: ReSWD. Sliced Wasserstein Distances are quite powerful, but they perform a Monte Carlo (MC) integration (over random directions). During an optimization this can lead to noisy gradients due to variance. Project page: reservoirswd.github.io

Dimitri Diakopoulos reposted

meshoptimizer v0.25 is out! Featuring new simplification function that optimizes positions and attributes for appearance, experimental permissive mode to simplify faceted regions with selective seam preservation, regularization option for improved tessellation quality and deformation, multiple ...

Dimitri Diakopoulos reposted

Choosing the right colormap is tricky, too often, they hide subtle details or distort the data. Our new method transforms colormaps to boost local contrast and reveal just noticeable differences, all while keeping the visualization perceptually accurate and accessible. dl.acm.org/doi/10.1145/...

Dimitri Diakopoulos reposted

Methods like NeRF and Gaussian Splats model the world as radioactive fog, rendered using alpha blending. This produces great results.. but are volumes the only way to get there?🤔 Our new SIGGRAPH'25 paper directly reconstructs surfaces without heuristics or regularizers.

Dimitri Diakopoulos reposted

One of my coworkers, @tearsofjake.bsky.social, has a talk at SIGGRAPH this year about this really cool steerable perlin noise technique that was used on Moana 2. He's just posted some handy reference implementations for Houdini, Unity, Godot, and Blender; check it out! github.com/jakericedesi...

github.comGitHub - jakericedesigns/SteerablePerlinNoise: Implementations of "Steerable Perlin Noise" as presented at Siggraph 2025Implementations of "Steerable Perlin Noise" as presented at Siggraph 2025 - jakericedesigns/SteerablePerlinNoise

Dimitri Diakopoulos reposted

⭐ Image editing without paired data, delivering on the promise of RGB<->X! Edit in Intrinsic space, get back your image with the desired modification! The method is quite fun too, conditional token optimization and noise inversion.

Iliyan Georgiev@iliyangeo.bsky.social

Editing appearance, geometry, lighting with precision is easy with a 3D scene representation. But it's so much more difficult with just an image or photograph. Enter IntrinsicEdit: Precise generative image manipulation in intrinsic space (SIGGRAPH 2025)! intrinsic-edit.github.io

Dimitri Diakopoulos reposted

Dimitri Diakopoulos reposted

Selena's #Siggraph25 work found a simple, nearly one-line change that greatly eases neural field optimization for a wide variety of existing representations. “Stochastic Preconditioning for Neural Field Optimization” by Selena Ling, Merlin Nimier-David, Alec Jacobson, & me.

Dimitri Diakopoulos reposted

Dimitri Diakopoulos reposted

A thread of thoughts on radiance fields, from my keynote at 3DV: Radiance fields have had 3 distinct generations. First was NeRF: just posenc and a tiny MLP. This was slow to train but worked really well, and it was unusually compressed --- The NeRF was smaller than the images.

Really love Daniel’s deep dives. Hits all the major notes: clearly written problem statement, excellent visualizations, and accessible solutions in code.

Daniel Holden@theorangeduck.bsky.social

Time for another long blog post... and today it's all about how we handle the temporal aspect of animation data. And more specifically, how to approach things from a signal processing perspective, covering up-sampling, down-sampling, and everything in-between. theorangeduck.com/page/filteri...