SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation

@article{Zhou2019SceneGraphNetNM,
  title={SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation},
  author={Y. Zhou and Zachary While and E. Kalogerakis},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={7383-7391}
}
In this paper we propose a neural message passing approach to augment an input 3D indoor scene with new objects matching their surroundings. [...] Key Method Our distribution is predicted though passing learned messages in a dense graph whose nodes represent objects in the input scene and edges represent spatial and structural relationships. By weighting messages through an attention mechanism, our method learns to focus on the most relevant surrounding scene context to predict new scene objects. We found that…Expand
18 Citations
Contextual Scene Augmentation and Synthesis via GSACNet
  • Highly Influenced
  • PDF
Retargetable AR: Context-aware Augmented Reality in Indoor Scenes based on 3D Scene Graph
  • PDF
Learning to generate new indoor scenes
  • 1
A Bottom-up Framework for Construction of Structured Semantic 3D Scene Graph
Learning Multi-View Camera Relocalization With Graph Neural Networks
  • 2
  • PDF
Holistic static and animated 3D scene generation from diverse text descriptions
Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
  • 4
  • PDF
SG-VAE: Scene Grammar Variational Autoencoder to Generate New Indoor Scenes
  • 1
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 31 REFERENCES
Deep Generative Modeling for Scene Synthesis via Hybrid Representations
  • 27
  • PDF
Deep convolutional priors for indoor scene synthesis
  • 89
  • Highly Influential
  • PDF
Learning 3D Scene Synthesis from Annotated RGB‐D Images
  • 26
  • PDF
GRAINS: Generative Recursive Autoencoders for INdoor Scenes
  • 64
  • Highly Influential
  • PDF
Semantic Scene Completion from a Single Depth Image
  • 627
  • Highly Influential
  • PDF
Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models
  • 34
  • PDF
A Generative Model of 3D Object Layouts in Apartments
  • 5
Automatic semantic modeling of indoor scenes from low-quality RGB-D data using contextual information
  • 89
  • PDF
Example-based synthesis of 3D object arrangements
  • 247
  • PDF
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
  • 3,714
  • PDF
...
1
2
3
4
...