AI Paper Atlas

Research map / 3D vision / Gaussian splatting

NeRF Is a Valuable Assistant for 3D Gaussian Splatting

Shuangkang Fang, I-Chao Shen, Takeo Igarashi, Yufeng Wang, ZeSheng Wang, Yi Yang, Wenrui Ding, Shuchang Zhou

ICCV 2025 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 15 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 edge-based initialization (ablation)NeRF-GS · Tanks&Temples avgPSNR: 22.61 -> 24.44Improved
add edge-based initialization (ablation)NeRF-GS · DeepBlending avgPSNR: 29.8 -> 30.7Improved
add feature sharing between NeRF and GS branches (ablation)NeRF-GS · Tanks&Temples avgPSNR: 23.93 -> 24.44Improved
add residual feature vector (ablation)NeRF-GS · Tanks&Temples avgPSNR: 24.09 -> 24.44Improved
add residual position vector (ablation)NeRF-GS · DeepBlending avgPSNR: 30.45 -> 30.7Improved
use GS-Rays instead of random rays for NeRF branch (ablation)NeRF-GS · DeepBlending avgPSNR: 30.22 -> 30.7Improved
add joint opacity loss (ablation)NeRF-GS · Tanks&Temples avgPSNR: 24.35 -> 24.44Improved
add joint RGB loss (ablation)NeRF-GS · DeepBlending avgPSNR: 30.59 -> 30.7Improved
add NeRF branch loss (joint NeRF training) (ablation)NeRF-GS · Tanks&Temples avgPSNR: 23.30 -> 24.44Improved
add volume regularization (ablation)NeRF-GS · Tanks&Temples avgPSNR: 24.29 -> 24.44Improved
add joint optimization after edge initialization instead of directly optimizing 3DGS (ablation)3DGS · DeepBlending avgPSNR: 29.89 -> 30.7Improved
use edge-based rather than random initialization for direct 3DGS (ablation)3DGS · Tanks&Temples avgPSNR: 23.65 -> 23.99Improved

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