AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Scaling Transformer-Based Novel View Synthesis with Models Token Disentanglement and Synthetic Data

Nithin Gopalakrishnan Nair, Srinivas Kaza, Xuan Luo, Vishal M. Patel, Stephen Lombardi, Jungyeon Park

ICCV 2025 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 1 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
replace shared LVSM blocks with Tok-D source/target modulationLVSM · RealEstate10kPSNR: 28.89 -> 30.02Improved
Tok-D versus LVSMLVSM · DL3DV in-distributionPSNR: 19.91 -> 21.55Improved
Tok-D versus LVSMLVSM · ACID in-distributionPSNR: 29.19 -> 29.47Improved
add synthetic data to training (ablation)LVSM · RealEstate10kPSNR: 28.89 -> 28.49Hurt
add synthetic data to training (ablation)LVSM · DL3DV cross-datasetPSNR: 20.52 -> 20.21Hurt
add synthetic data to training (ablation)Tok-D transformer · DL3DV cross-datasetPSNR: 21.18 -> 21.27Improved
add synthetic data to training (ablation)Tok-D transformer · RealEstate10kPSNR: 30.02 -> 29.97No clear effect
add real DL3DV data to training (ablation)Tok-D transformer · DL3DVPSNR: 21.27 -> 23.14Improved
add real DL3DV data to training (ablation)LVSM · DL3DVPSNR: 20.21 -> 21.37Improved
add pre-modulation of whole block input (ablation)Tok-D transformer · RealEstate10kPSNR: 28.50 -> 29.69Improved
add separate pre-modulation in attention and MLP only (ablation)Tok-D transformer · RealEstate10kPSNR: 28.50 -> 28.51No clear effect
add post-modulation scaling on top of pre-modulation (ablation)Tok-D transformer · RealEstate10kPSNR: 28.51 -> 30.02Improved

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