Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation

About

Despite advances in indoor 3D scene layout generation, synthesizing scenes with dense object arrangements remains challenging. Existing methods focus on large furniture while neglecting smaller objects, resulting in unrealistically empty scenes. Those that place small objects typically do not honor arrangement specifications, resulting in largely random placement not following the text description. We present Hierarchical Scene Motifs (HSM): a hierarchical framework for indoor scene generation with dense object arrangements across spatial scales. Indoor scenes are inherently hierarchical, with surfaces supporting objects at different scales, from large furniture on floors to smaller objects on tables and shelves. HSM embraces this hierarchy and exploits recurring cross-scale spatial patterns to generate complex and realistic scenes in a unified manner. Our experiments show that HSM outperforms existing methods by generating scenes that better conform to user input across room types and spatial configurations. Project website is available at https://3dlg-hcvc.github.io/hsm .

Hou In Derek Pun, Hou In Ivan Tam, Austin T. Wang, Xiaoliang Huo, Angel X. Chang, Manolis Savva• 2025

Related benchmarks

TaskDatasetResultRank
Indoor Scene Generation179 room-level prompts
Realism Win Rate88.5
12
3D indoor scene generationShort-text 3D indoor scene generation setting
Collision Rate9.36
6
Room-Level Scene SynthesisSceneEval room-level 30 prompts
CNT Score53.3
4
3D indoor scene generationHSSD-200 (test)
OP Score7.26
3
Showing 4 of 4 rows

Other info

Follow for update