Scene Graph Generation by Iterative Message Passing
This work addresses the challenge of understanding visual scenes beyond object recognition, which is important for applications in computer vision and robotics, but it is incremental as it builds on existing scene graph generation techniques.
The paper tackles the problem of generating scene graphs from images by modeling objects and their relationships, proposing an end-to-end model that uses RNNs and iterative message passing for joint inference. The result is a significant performance improvement over previous methods on the Visual Genome and NYU Depth v2 datasets.
Understanding a visual scene goes beyond recognizing individual objects in isolation. Relationships between objects also constitute rich semantic information about the scene. In this work, we explicitly model the objects and their relationships using scene graphs, a visually-grounded graphical structure of an image. We propose a novel end-to-end model that generates such structured scene representation from an input image. The model solves the scene graph inference problem using standard RNNs and learns to iteratively improves its predictions via message passing. Our joint inference model can take advantage of contextual cues to make better predictions on objects and their relationships. The experiments show that our model significantly outperforms previous methods for generating scene graphs using Visual Genome dataset and inferring support relations with NYU Depth v2 dataset.