AI Paper Atlas

Research map / 3D vision / 3D generation

GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation

Nicolas von Lützow, Barbara Roessle, Katharina Schmid, Matthias Niessner

ECCV 2026 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use xyz column-wise serialization instead of Z-order (ablation)GaussianGPT · ASE+3D-FRONTvalidation cross-entropy: 2.432 -> 2.421Improved
use xyz serialization instead of Hilbert curve (ablation)GaussianGPT · ASE+3D-FRONTvalidation cross-entropy: 2.439 -> 2.421Improved
use xyz serialization instead of transposed Z-order (ablation)GaussianGPT · ASE+3D-FRONTvalidation cross-entropy: 2.423 -> 2.421No clear effect
add separate vocabularies for position and feature tokens (ablation)GaussianGPT · ASE+3D-FRONTvalidation cross-entropy: 2.449 -> 2.421Improved
use 3D RoPE instead of learned positional embeddings (ablation)GaussianGPT · ASE+3D-FRONTvalidation cross-entropy: 2.461 -> 2.421Improved
use 3D RoPE instead of 1D RoPE (ablation)GaussianGPT · ASE+3D-FRONTvalidation cross-entropy: 2.446 -> 2.421Improved
reduce autoencoder downsampling from 3x to 1x (ablation)autoencoder · 3D-FRONT reconstructionPSNR: 21.11 -> 24.34Improved
reduce autoencoder downsampling from 3x to 2x (ablation)autoencoder · 3D-FRONT reconstructionPSNR: 21.11 -> 23.73Improved
increase codebook size from 4096 to 16384 (ablation)autoencoder · 3D-FRONT reconstructionPSNR: 21.11 -> 21.37Mixed
decrease codebook size from 4096 to 1024 (ablation)autoencoder · 3D-FRONT reconstructionPSNR: 21.11 -> 20.93Hurt
use standard VQ instead of LFQ (ablation)autoencoder · 3D-FRONT reconstructionPSNR: 21.11 -> 21.59Mixed
add resampling retries for empty columns (5 or 15 retries vs 0) (ablation)GaussianGPT outpainting · 12m x 12m scene KID degradationKIDImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy