Diego Gomez

Research Scientist Intern @ Meta | PhD student @ LIX | BX 2021 | MVA | Working on topics at the intersection of CG, CV and ML.

[Diego Gomez @DiegoGomezLIX]

1/n 🧵 Introducing Gaussian Wrapping — a principled framework for extracting high-quality meshes from 3DGS! 🚲
We recover thin structures, like bicycle spokes, where all prior methods fail.

Follow the thread for a brief overview and links!

[Antoine Guédon @antoine_guedon]

🎉Surflo is a NeurIPS 2026 Oral!
Huge thanks to my coauthors @nico_dufour @ShuNakamuraW @JiahuiLei1998 @kyoto_vision @akanazawa, and to the reviewers and AC.

Code, model and data are released. Check it out if you're into feed-forward 3D and flow matching!
https://t.co/lBcJRgpN2O

[Nicolas DUFOUR @nico_dufour]

Very funny how every workshop was about moving away from explicit 3D but the best paper awards look like SIGGRAPH.

More and more people not doing 3D are migrating away from vision conferences to learning conferences.

A bit sad but given the signal CVPR/ECCV/ICCV gives....

[Antoine Guédon @antoine_guedon]

We've just released code+model for Surflo!🚀
Turn any number of photos into a 3D surface with Flow Matching.

Our latent representation encodes the full scene and can be queried for downstream applications like 3D segmentation.

🔗https://t.co/lBcJRgpfdg
💻https://t.co/XpHQtmZHXJ

[Diego Gomez @DiegoGomezLIX]

🎉 Gaussian Wrapping is accepted to ECCV 2026! Grateful to my incredible collaborators 🙌 See you in Malmö ���🇪 #ECCV2026

[Diego Gomez @DiegoGomezLIX]

1/n 🧵 Introducing Gaussian Wrapping — a principled framework for extracting high-quality meshes from 3DGS! 🚲
We recover thin structures, like bicycle spokes, where all prior methods fail.

Follow the thread for a brief overview and links!

[Diego Gomez @DiegoGomezLIX]

I'm excited to share that I've joined Meta's Codec Labs Team in the Bay Area as a Research Scientist Intern.

If you're nearby and want to grab a coffee, drop me a message. And I'd welcome any recommendations for the best food and things to do in the area!

[Antoine Guédon @antoine_guedon]

What if you could turn any number of photos (3, 8, 15, or even 60) into one clean 3D surface (pts & mesh) with Flow Matching?

Check out our new work, Surflo: Consistent 3D Surface Flow Model with Global State. 🧵
1/n

🔗https://t.co/lBcJRgpfdg

[Erkan Turan @erkanhturan]

Can a linear operator capture what a flow model does?

Surprisingly, yes, if you lift into the right space. We use Koopman theory to linearize the full generative trajectory of a flow model, unlocking spectral analysis and editing.

📍 #ICML2026, Seoul

Code and paper below.

[Erkan Turan @erkanhturan]

Why are GNNs stuck at 2–4 layers? Deep ones “oversmooth”, every node collapses to the same vector.

Our fix needs no residual connections, no normalization, no rewiring. Just swap the activation function.

📍Spotlight #ICML2026 , Seoul

Link to paper at end of thread.

[Diego Gomez @DiegoGomezLIX]

[Small Update] You can now easily try Gaussian Wrapping on synthetic scenes! 🌭🛳️🪴

Mesh obtained with PAM (2M vertices).

Link to script: https://t.co/QvxCpmzUaN

[Diego Gomez @DiegoGomezLIX]

1/n 🧵 Introducing Gaussian Wrapping — a principled framework for extracting high-quality meshes from 3DGS! 🚲
We recover thin structures, like bicycle spokes, where all prior methods fail.

Follow the thread for a brief overview and links!

[Léopold @LeopoldMaillard]

Generative models can create visually stunning 3D rooms, but are they functional for the agents inside them? 🛋️🤖

Introducing SceneTeract - a framework that verifies 3D scene functionality under agent-specific constraints!

📄: https://t.co/ZCc822hMPU
🌐: https://t.co/nFkP0nuIba

[Diego Gomez @DiegoGomezLIX]

8/n Huge thanks to my co-authors @antoine_guedon , Nissim Maruani, @gongbingchen , and @maks_ovsjanikov,the supporting institutions, and to the "Objects as Volumes" team for the inspiring framework! 🙏

Check out the full paper and code here: https://t.co/zWKV62RtEb

[Diego Gomez @DiegoGomezLIX]

7/n Primal Adaptive Meshing (PAM)🕸️
Standard meshing ties vertices to Gaussian positions, so resolution is stuck.

PAM fully decouples mesh resolution from the Gaussians, enabling region-of-interest meshing at arbitrary resolution. 🚀

[MrNeRF @janusch_patas]

From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians

TL;DR: Gaussian Wrapping interprets 3D Gaussians as stochastic, oriented surface elements and derives closed-form vacancy and normal fields, enabling fast, watertight, and compact mesh extraction of full 3D scenes.

Contributions:
– We introduce Oriented-Gaussians and their associated training strategy in the multi-view setting.

– We derive a theoretical connection between 3DGS and implicit surface reconstruction by formulating Gaussians as oriented surface elements, inspired by Objects as Volumes [39]. Importantly, this leads to closed-form expressions for both normal and occupancy fields at arbitrary locations without any additional learnable parameters.

– We propose Primal Adaptive Meshing, a mesh extraction procedure that leverages the derived Gaussian fields to produce high-quality, water-tight meshes at controllable resolution, enabling recovery of extremely thin structures such as bicycle spokes (Fig. 1).

[Erkan Turan @erkanhturan]

Generative Drifting achieves SOTA 1-step image generation.

But why does it work?

We show that optimal transport and, surprisingly, plasma physics, allow us to answer 4 key questions

Preprint here: https://t.co/iGrkvjPRNQ

Details below.