activity
20152025
most citedMatterport3D: Learning from RGB-D Data in Indoor Environments

337 citations · 867 across the 48 of their papers we have counts for

collaborators
Showing cs.GRShow all

7 papers · 1 filter

cs.GR2025

SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesis

Xiaohao Sun, Divyam Goel, Angel X. Chang

We present SemLayoutDiff, a unified model for synthesizing diverse 3D indoor scenes across multiple room types. The model introduces a scene layout representation combining a top-d…

cs.GR2025

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

Hou In Derek Pun, Hou In Ivan Tam, Austin T. Wang +3

Despite advances in indoor 3D scene layout generation, synthesizing scenes with dense object arrangements remains challenging. Existing methods focus on large furniture while negle…

cs.GR2025

SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis

Hou In Ivan Tam, Hou In Derek Pun, Austin T. Wang +2

Despite recent advances in text-conditioned 3D indoor scene generation, there remain gaps in the evaluation of these methods. Existing metrics often measure realism by comparing ge…

cs.GR2025

Learning to Place Objects with Programs and Iterative Self Training

Adrian Chang, Kai Wang, Yuanbo Li +3

In this work we study indoor scene object placement. Given a 3D indoor scene and an object, the task is to predict placement locations within the scene. Empirical observations of d…

cs.GR2024

SceneMotifCoder: Example-driven Visual Program Learning for Generating 3D Object Arrangements

Hou In Ivan Tam, Hou In Derek Pun, Austin T. Wang +2

Despite advances in text-to-3D generation methods, generation of multi-object arrangements remains challenging. Current methods exhibit failures in generating physically plausible…

cs.GR2017★ 10 cited

SceneSuggest: Context-driven 3D Scene Design

Manolis Savva, Angel X. Chang, Maneesh Agrawala

We present SceneSuggest: an interactive 3D scene design system providing context-driven suggestions for 3D model retrieval and placement. Using a point-and-click metaphor we specif…