AI Paper Atlas

Research map / 3D vision / Gaussian splatting

CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image

Wonseok Roh, Hwanhee Jung, Jong Wook Kim, Seunggwan Lee, Innfarn Yoo, Andreas Lugmayr, Seunggeun Chi, Karthik Ramani, Sangpil Kim

ICCV 2025 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 9 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 contextual prior from VLM text embeddings via cross-attention (ablation)CATSplat baseline transformer · RE10K (n=Random)PSNR: 25.02 -> 25.40Improved
add spatial prior from 3D point features via cross-attention (ablation)CATSplat baseline transformer · RE10K (n=Random)PSNR: 25.02 -> 25.42Improved
combine both priors (ablation)CATSplat · RE10K (n=Random)PSNR: 25.02 -> 25.45Improved
use pretrained visual encoder features (DINOv2, ConvNeXt) instead of the proposed priors (ablation)CATSplat cross-attention · RE10K (n=Random)PSNR: 25.40 -> 25.17 (DINOv2-g vs contextual)Hurt
use single-sentence text description rather than scene type or object list (ablation)contextual prior · RE10K (n=Random)PSNR: 25.13 -> 25.40Improved
extend text description to two or more sentences (ablation)contextual prior · RE10K (n=Random)PSNR: 25.40 -> 25.29Hurt
concatenate depth with image (ablation)baseline transformer · RE10K (n=Random)PSNR: 24.82 -> 25.02Improved
replace depth concatenation with unprojected 3D point concatenation (ablation)baseline transformer · RE10K (n=Random)PSNR: 25.02 -> 25.04No clear effect
cross-attend point features rather than depth features (ablation)spatial prior · RE10K (n=Random)PSNR: 25.16 -> 25.42Improved
increase number of cross-attention layers from one to three (ablation)CATSplat · RE10K qualitativeimage error mapsImproved
use CATSplat instead of Flash3D for extrapolationsingle-view 3DGS · RE10K extrapolationPSNR: 24.10 -> 25.35Improved
single-view CATSplat versus two-view MVSplat on interpolationRE10K interpolation · RE10K interpolationPSNR: 26.39 vs 25.23Hurt

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