AI Paper Atlas

Research map / 3D vision / Gaussian splatting

FPGS: Feed-Forward Semantic-aware Photorealistic Style Transfer of Large-Scale Gaussian Splatting

GeonU Kim, Kim Youwang, Lee Hyoseok, Tae-Hyun Oh

IJCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 2 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 FPGS instead of FPRFFPRF · LLFFmulti-view error (short): 0.0231 -> 0.0214Improved
use FPGS instead of StyleGaussianStyleGaussian · LLFFmulti-view error (long): 0.0440 -> 0.0349Improved
use FPGS instead of FPRFFPRF · San Francisco Mission Baymulti-view error (long): 0.0563 -> 0.0502Improved
use FPGS instead of FPRFFPRF · LLFFtotal training time (min): 61 -> 24Improved
use FPGS instead of FPRFFPRF · LLFFrender time (sec): 3.812 -> 0.004Improved
use FPGS instead of UPST-NeRFUPST-NeRF · LLFF user studyPST quality rating: 3.279 -> 3.936Improved
add semantic matching with semantic-weighted local AdaIN (ablation)FPGS · LLFFperceptual style similarityImproved
add iterative style transfer (ablation)FPGS · LLFFlocal style transfer qualityImproved
use DINO instead of Stable Diffusion v1-5 or DINOv2 as semantic encoder (ablation)FPGS · LLFFstylization quality (qualitative)Improved

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