CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhai, Guangyao, Örnek, Evin Pınar, Wu, Shun-Cheng, Di, Yan, Tombari, Federico, Navab, Nassir, Busam, Benjamin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916077413335040
author Zhai, Guangyao
Örnek, Evin Pınar
Wu, Shun-Cheng
Di, Yan
Tombari, Federico
Navab, Nassir
Busam, Benjamin
author_facet Zhai, Guangyao
Örnek, Evin Pınar
Wu, Shun-Cheng
Di, Yan
Tombari, Federico
Navab, Nassir
Busam, Benjamin
contents Controllable scene synthesis aims to create interactive environments for various industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner. Existing methods, reliant on retrieval from extensive databases or pre-trained shape embeddings, often overlook scene-object and object-object relationships, leading to inconsistent results due to their limited generation capacity. To address this issue, we present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes, which are semantically realistic and conform to commonsense. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes via latent diffusion, capturing global scene-object and local inter-object relationships in the scene graph while preserving shape diversity. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model. Due to lacking a scene graph dataset offering high-quality object-level meshes with relations, we also construct SG-FRONT, enriching the off-the-shelf indoor dataset 3D-FRONT with additional scene graph labels. Extensive experiments are conducted on SG-FRONT where CommonScenes shows clear advantages over other methods regarding generation consistency, quality, and diversity. Codes and the dataset will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2305_16283
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion
Zhai, Guangyao
Örnek, Evin Pınar
Wu, Shun-Cheng
Di, Yan
Tombari, Federico
Navab, Nassir
Busam, Benjamin
Computer Vision and Pattern Recognition
Controllable scene synthesis aims to create interactive environments for various industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner. Existing methods, reliant on retrieval from extensive databases or pre-trained shape embeddings, often overlook scene-object and object-object relationships, leading to inconsistent results due to their limited generation capacity. To address this issue, we present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes, which are semantically realistic and conform to commonsense. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes via latent diffusion, capturing global scene-object and local inter-object relationships in the scene graph while preserving shape diversity. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model. Due to lacking a scene graph dataset offering high-quality object-level meshes with relations, we also construct SG-FRONT, enriching the off-the-shelf indoor dataset 3D-FRONT with additional scene graph labels. Extensive experiments are conducted on SG-FRONT where CommonScenes shows clear advantages over other methods regarding generation consistency, quality, and diversity. Codes and the dataset will be released upon acceptance.
title CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2305.16283