AI Paper Atlas

Research map / 3D vision / Gaussian splatting

TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens

Jiawei Ren, Michal Jan Tyszkiewicz, Jiahui Huang, Zan Gojcic

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 12 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
add visibility loss (ablation)TokenGS · RealEstate10K (4 views)PSNR: 0.4 PSNR improvementImproved
increase Gaussian tokens from 1024 to 4096 (finetune) (ablation)TokenGS · RealEstate10K (2 views)PSNR: 28.02 -> 28.41Improved
add token tuning (ablation)TokenGS (4096 tok) · RealEstate10K (2 views)PSNR: 28.41 -> 28.82Improved
add token tuning (ablation)TokenGS · DL3DV 4 viewsPSNR: 23.02 -> 23.57Improved
add token tuning (ablation)TokenGS (zero-shot 6-view) · DL3DV 6 viewsPSNR: 23.69 -> 24.51Improved
add token tuning (ablation)TokenGS (zero-shot 2-view) · DL3DV 2 viewsPSNR: 19.35 -> 19.32No clear effect
tune Gaussian parameters directly instead of tokens (ablation)TokenGS · DL3DV (test-time)PSNR and geometryMixed
extend context to up to 4x more views than trained (ablation)TokenGS (4-view base) · DL3DVPSNRImproved
add more token-tuning steps (10 up to 250) (ablation)TokenGS · DL3DVPSNRImproved
directly regress 3D means instead of per-pixel depth (vs GS-LRM)TokenGS · RealEstate10K camera noise (2 views)PSNR and LPIPS gapImproved
replace PM-loss finetuned DepthSplat with TokenGSDepthSplat+PM · DL3DV view extrapolationPSNR: 20.77 -> 20.98Improved
use TokenGS instead of BTimerBTimer · Kubric 4DPSNR: 24.45 -> 24.84Improved

Later papers that compared with this method

1 later accepted paper reports TokenGS as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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