AI Paper Atlas

Research map / 3D vision / 3D generation

VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling

Hyojun Go, Byeongjun Park, Hyelin Nam, Byung-Hoon Kim, Hyungjin Chung, Changick Kim

ICCV 2025 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 7 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 asynchronous sampling (delta=0.2) (ablation)VideoRFSplat vanilla sampling · T3BenchBRISQUE: 34.9 -> 32.2Improved
add asynchronous sampling (delta=0.2) (ablation)VideoRFSplat vanilla sampling · T3BenchNIQE: 5.32 -> 4.20Improved
add modified CFG to asynchronous sampling (delta=0.2) (ablation)VideoRFSplat · T3BenchBRISQUE: 34.1 -> 32.2Improved
increase delta from 0.2 to 0.5 with async sampling (ablation)VideoRFSplat · T3BenchBRISQUE: 32.2 -> 34.4Hurt
add asynchronous sampling with 200 steps (ablation)VideoRFSplat · T3BenchBRISQUE: 33.8 -> 31.8Improved
add timestep division in training (Eq. 4) (ablation)VideoRFSplat vanilla sampling · T3BenchBRISQUE: 35.3 -> 34.9No clear effect
use dual-stream architecture instead of channel concatenation (ablation)joint pose-image generation · T3BenchNIQE: 7.83 -> 6.19Improved
use dual-stream architecture instead of channel concatenation (ablation)joint pose-image generation · T3BenchCLIPScore: 29.8 -> 32.5Improved
use VideoRFSplat without SDS++ instead of SplatFlowtext-to-3DGS · MVImgNet valFID-10K: 34.85 -> 30.33Improved
add SDS++ refinement to SplatFlowSplatFlow · MVImgNet valFID-10K: 34.85 -> 35.46Hurt
add SDS++ refinement to Director3DDirector3D · DL3DV valFID-2.4K: 88.44 -> 95.88Hurt
use VideoRFSplat instead of CameraCtrlcamera-conditioned generation · RealEstate10KFID-8K: 62.97 -> 43.07Improved

Later papers that compared with this method

1 later accepted paper reports VideoRFSplat as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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