AI Paper Atlas

Research map / 3D vision / 3D generation

SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation With Fine-Grained Geometry

Lin Gao, Jia-Mu Sun, Kaichun Mo, Yu‐Kun Lai, Leonidas J. Guibas, Jie Yang

TPAMI 2023 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 69 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 object-object edges (ablation)SceneHGN · 3D-FRONT generationFID: 145.398 -> 106.005Improved
add room-object edges (ablation)SceneHGN · 3D-FRONT generationFID: 150.478 -> 106.005Improved
add hyper-edges (ablation)SceneHGN · 3D-FRONT generationFID: 130.276 -> 106.005Improved
add hyper-edges (ablation)SceneHGN · 3D-FRONT generationo3: 1.553 -> 0.470Improved
add functional regions as intermediate level (ablation)SceneHGN · 3D-FRONT reconstructionCD (x10^-5): 398.1 -> 310.7Improved
add functional regions as intermediate level (ablation)SceneHGN · 3D-FRONT generationFID: 135.940 -> 106.005Improved
separate (multi-stage) training instead of end-to-end (ablation)SceneHGN · 3D-FRONT reconstructionCD (x10^-5): 473.9 -> 315.2Improved
separate (multi-stage) training instead of end-to-end (ablation)SceneHGN · 3D-FRONT generationFID: 170.079 -> 139.450Improved
jointly model layout and part geometry vs ATISSSceneHGN vs ATISS · 3D-FRONT generationFID: 141.7889 -> 139.4508Improved
hierarchical joint generation vs GRAINSSceneHGN vs GRAINS · 3D-FRONT generationo1: 0.30 -> 0.05Improved
SceneHGN vs GRAINS on orientationSceneHGN vs GRAINS · 3D-FRONT generationorientation score: 0.9931 -> 0.9572Hurt
SceneHGN vs ATISS on orientationSceneHGN vs ATISS · 3D-FRONT generationorientation score: 0.9578 -> 0.9572No clear effect

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