AI Paper Atlas

Research map / 3D vision / Gaussian splatting

TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction

Yihui Li, Chengxin Lv, Zichen Tang, Hongyu Yang, Di Huang

CVPR 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 10 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 token-aligned Gaussian prediction instead of a pixel-aligned head (ablation)TokenSplat · RE10K (8 views)PSNR (dB): 25.33 -> 26.15Improved
use token-aligned Gaussian prediction instead of a pixel-aligned head (ablation)TokenSplat · RE10K (8 views)RPE-r: 0.496 -> 0.458Improved
use token-based fusion instead of AnySplat-style Gaussian fusion (ablation)TokenSplat · RE10K (8 views)PSNR (dB): 25.77 -> 26.15Improved
add the ADF-Decoder instead of a standard ViT decoder (ablation)TokenSplat · RE10K (8 views)PSNR (dB): 25.88 -> 26.15Improved
add the ADF-Decoder instead of a standard ViT decoder (ablation)TokenSplat · RE10K (8 views)RPE-r: 0.504 -> 0.458Improved
add the ADF-Decoder instead of a standard ViT decoder (ablation)TokenSplat · RE10K (8 views)ATE: 0.023 -> 0.012Improved
add the known intrinsic camera embedding (ablation)TokenSplat · RE10K (8 views)PSNR (dB): 25.54 -> 26.15Improved
add the known intrinsic camera embedding (ablation)TokenSplat · RE10K (8 views)RPE-r: 0.471 -> 0.458No clear effect
use TokenSplat instead of pose-required FreeSplatFreeSplat · RE10K (8 views)PSNR (dB): 25.20 -> 26.15Improved
increase test views to 28 using a model trained with 10 viewsTokenSplat · multi-view Table 2PSNR (dB): 26.83 -> 26.87No clear effect
increase test views from 10 to 28FreeSplat · multi-view Table 2PSNR (dB): 25.38 -> 24.30Hurt
increase test views from 10 to 28NoPoSplat · multi-view Table 2PSNR (dB): 24.21 -> 23.21Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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