SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation
In this paper we propose a neural message passing approach to augment an input 3D indoor scene with new objects matching their surroundings. Given an input, potentially incomplete, 3D scene and a query location, our method predicts a probability distribution over object types that fit well in that location. 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 our method significantly outperforms state-of-the-art approaches in terms of correctly predicting objects missing in a scene based on our experiments in the SUNCG dataset. We also demonstrate other applications of our method, including context-based 3D object recognition and iterative scene generation.
Application I. Object recommendation for query locations (comparison with state-of-the-art methods)
Application II. Iterative scene synthesis
Application III. Context-based object recognition. Left: Object recognition using a multi-view CNN without considering the scene context. Right: Improved recognition by fusing the multi-view CNN and SceneGraphNet predictions based on scene context.
Yang Zhou, Zachary While, Evangelos Kalogerakis, "SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation", ICCV 2019
Source Code & Data
Github code: https://github.com/yzhou359/3DIndoor-SceneGraphNet
SUNCG Dataset: http://suncg.cs.princeton.edu [currently is down :( ]
This research is funded by NSF(CHS-161733). Our experiments were performed in the UMass GPU cluster obtained under the Collaborative Fund managed by the Massachusetts Technology Collaborative.