George Shramko

MSc student @ Simon Fraser University

[George Shramko @hekoshii]

@willeastcott @playcanvas Looks cool! Could you share the capture data? Trying out a new representation

[Yizheng Xie @yizheng_xie]

Rule #1 of 3DGS capture: don't touch anything! Open a door and it messes up your whole scene. 🚪

But what if you do?

𝐒𝐰𝐢𝐭𝐜𝐡𝐒𝐩𝐥𝐚𝐭 (SIGGRAPH Asia 2026) turns what you touched into switches you can flip 👇

https://t.co/I2OfUBvCeL

[Andrea Tagliasacchi @taiyasaki]

📢📢📢 𝐒𝐰𝐢𝐭𝐜𝐡𝐒𝐩𝐥𝐚𝐭: Learning Discrete Object States from Casually Captured Scenes

Co-lead by Yizheng Xie and Yalda Foroutan
To be presented at SIGGRAPH Asia 2026

𝐋𝐢𝐯𝐞 𝐝𝐞𝐦𝐨: https://t.co/bWVGAWRsw7
arXiv: https://t.co/Xn0DX3R4J4
(video with 🔊)

[Ke Li 🍁 @KL_Div]

VLA policies are slow and jerky. Introducing IMLE-VLA, which swaps out flow matching for conditional IMLE. IMLE-VLA generates action chunks at 55 Hz (3.67x faster than π0.5), produces >2.2x less jerk and finishes tasks >3.9x faster.

Details at https://t.co/axlJ1JcaWg

If you are at #IROS2026, don't miss @kianhk3's talk on Monday at 9am in Room 329.

Joint work w/ @kianhk3, Qinhe Peng, @hekoshii, @mehranag, @jianing_qian, @tristanengst, @Moazeni_Alireza and @dineshjayaraman

Thread 👇

1/8

[Ke Li 🍁 @KL_Div]

Editing texture in 3DGS results in artifacts that become especially pronounced when the geometry changes.

Introducing Point-GT, which learns a UV map that adapts automatically to deformations with PAPR.

Joint w/ @yszhang170, @hekoshii and @_pratul_.

Project Website: https://t.co/WqQs7kROcZ
Paper: https://t.co/9Ho4r9cn7Q
Code: https://t.co/7aJtMwHccW
Video: https://t.co/HzAGiODDCC

If you are at #ECCV2026, come check out poster #206 this Thursday morning at 10:30am!

[Andrea Tagliasacchi @taiyasaki]

📢📢📢introducing 𝐏𝐨𝐰𝐞𝐫 𝐅𝐨𝐚𝐦

A 3D representation that can be ray traced or rasterized in real time, with NO COMPROMISE in quality.

- Project: https://t.co/LkmVQjkIt2
- arXiv: https://t.co/TtMbyKrvrp

Rasterized at 3DGS-class FPS
Ray traced at Radiant Foam speeds

[Ahan @ahan_sh]

Excited to share our recent work: Free-Range Gaussians 🥚✨

The core idea: instead of predicting Gaussians on a pixel- or voxel-aligned grid, we let them live freely in 3D space.

🌐 Project: https://t.co/HkwmGam0Pq
📝 Paper: https://t.co/OhHA6VnwZT

[Andrea Tagliasacchi @taiyasaki]

📢📢📢 Introducing "FullCircle: Effortless 3D Reconstruction from Casual 360° Captures"

TL;DR: 10x faster casual capture with clean reconstructions

Homepage: https://t.co/zbnH024bNT
Code: https://t.co/d4HcFpsFYR
arXiv: https://t.co/eDOP3napAl

Led by Yalda Foroutan & Ipek Oztas