Sign in

Diego Gomez

@diegoxgomez.bsky.social
39 followers 68 following 10 posts

PhD student @ LIX | BX 21 | MVA 23 diego1401.github.io

PostsRepliesMedia
Diego Gomez @diegoxgomez.bsky.social · 09/04/2026
8/n Huge thanks to my co-authors @antoine-guedon.bsky.social, Nissim Maruani, @s2.hk, 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: diego1401.github.io/BlobsToSpoke...
diego1401.github.io
From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians
Gaussian Wrapping: a principled framework that interprets 3D Gaussians as oriented surface elements, deriving closed-form occupancy and normal fields for high-fidelity, watertight mesh reconstruction of complete 3D scenes.
010
Diego Gomez @diegoxgomez.bsky.social · 09/04/2026
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. 🚀
130
Diego Gomez @diegoxgomez.bsky.social · 09/04/2026
6/n 🛡️How do we ensure no gaps? Two complementary mechanisms: 1️⃣ Normal alignment loss: aligns rendered normals with image-space depth gradients. 2️⃣ Normal-aware densification: detects gaps in the shell, clones Gaussians with flipped normals, and closes the holes.
130
Diego Gomez @diegoxgomez.bsky.social · 09/04/2026
5/n 🌊Gaussian Vector & Normal Fields, once Gaussians wrap the scene, the "Objects as Volumes" framework [Miller et al.] yields closed-form expressions for occupancy & normal fields. The Vector Field V(x) encodes geometry directly from 3DGS params!
120
Diego Gomez @diegoxgomez.bsky.social · 09/04/2026
4/n🔧Our fix: give each Gaussian a learnable oriented normal n. ⬅️ This makes it an oriented stochastic surface element with a clear inside/outside. The Gaussian models density decay on the outward side, while the inward side is treated as fully occupied.
120
Diego Gomez @diegoxgomez.bsky.social · 09/04/2026
3/n ⛈️ The root problem: 3DGS treats each Gaussian as a symmetric blob of density. But surfaces are asymmetric — they separate empty space from occupied matter. Modelling surface points with symmetric primitives introduces a fundamental reconstruction bias.
120
Diego Gomez @diegoxgomez.bsky.social · 09/04/2026
2/n Links & Resources: 📄 Arxiv: arxiv.org/abs/2604.07337 🌐Project: diego1401.github.io/BlobsToSpoke... 🎬 Video: youtube.com/watch?v=zOwN... 💻 Code: github.com/diego1401/Ga...
110
Diego Gomez @diegoxgomez.bsky.social · 09/04/2026
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!
1175
Diego Gomez @diegoxgomez.bsky.social · 14/12/2025
Link to our talk. sa2025.conference-schedule.org/presentation...
sa2025.conference-schedule.org
Presentation
000
Diego Gomez @diegoxgomez.bsky.social · 14/12/2025
I’ll be at #SIGGRAPHAsia2025 next week presenting our paper MILo! Join the Neural Fields and Surface Reconstruction session on Tuesday, December 16. If you’ll be in Hong Kong and would like to discuss research, or grab a coffee ☕️ feel free to reach out.
183
Reposted by Diego Gomez
Antoine Guédon @antoine-guedon.bsky.social · 08/09/2025
1/n🚀Gaussians > Differentiable function > Mesh? Check out our new work: MILo: Mesh-In-the-Loop Gaussian Splatting! 🎉Accepted to SIGGRAPH Asia 2025 (TOG) MILo is a novel differentiable framework that extracts meshes directly from Gaussian parameters during training. 🧵👇
3237