GaussianGPT Releases Code for Token-by-Token 3D Gaussian Scene Generation
“📢GaussianGPT (ECCV'26) Code Release📢 What if 3D scenes worked like language? Generate full 3D Gaussian scenes - from scratch or from partial - token by token! 🔗https://github.com/nicolasvonluetzow/GaussianGPT 🌐https://nicolasvonluetzow.github.io/GaussianGPT Great work by @nicolasvluetzow, @barbara_roessle, @katha_schmid https://x.com/MattNiessner/status/2074853765706842522/video/1”
MattNiessnerTECH#1304GaussianGPT Releases Code for Token-by-Token 3D Gaussian Scene Generation is circulating through @MattNiessner, with the visible post framing the story around a code release for GaussianGPT. So far, the public evidence is narrow, so the safest read is what the post says and what remains unverified. The useful read for readers is therefore limited but clear: what was claimed, who put it in front of the conversation, and what would need more confirmation before anyone treats it as settled.
- GaussianGPT Releases Code for Token-by-Token 3D Gaussian Scene Generation is safest to read as an attributed public claim, not an independently settled fact.
- The visible conversation gives readers a useful signal about attention, but it does not replace source confirmation.
Visible reactions are too thin to support a broad read of public sentiment. available sources show attention on the post, but not enough visible reaction evidence to characterize a wider public response.