AI Paper Atlas

Research map / 3D vision / 3D generation

MiDSummer: Multi-Guidance Diffusion for Controllable Zero-Shot Immersive Gaussian Splatting Scene Generation

Anjun Hu, Richard Tomsett, Valentin Gourmet, Massimo Camplani, Jas Kandola, Hanting Xie

ICCV 2025 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 0 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 GDM guidance to LLM-only layoutLLM-only layout · SUN RGB-D text-to-layoutL/R accuracy: 47.5 -> 88.8Improved
add LLM guidance to GDM-only layoutGDM-only layout · SUN RGB-D text-to-layoutVolume error: 255.5 -> 50.8Improved
add LLM guidance to GDM-only layoutGDM-only layout · SUN RGB-D text-to-layoutBi/Sm accuracy: 76.4 -> 88.8Improved
add LLM guidance to GDM-only layoutGDM-only layout · SUN RGB-D text-to-layoutU/D accuracy: 89.0 -> 87.4Hurt
add LLM guidance to GDM-only layout (scene graph input)GDM-only layout · SUN RGB-D scene-graph-to-layoutVolume error: 332.7 -> 64.2Improved
add LLM guidance to GDM-only layout (scene graph input)GDM-only layout · SUN RGB-D scene-graph-to-layoutL/R accuracy: 89.5 -> 84.0Hurt
add dual-guidance layout planning (ablation)MiDSummer · text-to-scene generationKID vs SUN RGB-D: 0.1198 -> 0.0647Improved
add dual-guidance layout planning (ablation)MiDSummer · text-to-scene generationVarLap: 615.4 -> 633.8Improved
add layout-aware refinement (ablation)MiDSummer · text-to-scene generationVarLap: 545.9 -> 633.8Improved
add layout-aware refinement (ablation)MiDSummer · text-to-scene generationKID vs SUN RGB-D: 0.0569 -> 0.0647Hurt
use equal 0.5/0.5 GDM/LLM weights instead of GDM only (ablation)layout diffusion · SUN RGB-D text-to-layoutMean binary relationship accuracy: 84.22 -> 71.61Hurt
shift weight from GDM to LLM (1.0/0.0 to 0.0/1.0) (ablation)layout diffusion · SUN RGB-D text-to-layoutVolume error: 255.5 -> 64.5Improved

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