Specifying Object Attributes and Relations in Interactive Scene Generation
This work addresses the challenge of interactive scene generation for users needing fine-grained control over object attributes and relations, though it appears incremental as it builds on existing scene graph methods.
The authors tackled the problem of generating images from scene graphs by introducing a method that uses separate layout and appearance embeddings, resulting in images that better match the scene graph, have higher visual quality, and support more complex scenes with multiple diverse outputs.
We introduce a method for the generation of images from an input scene graph. The method separates between a layout embedding and an appearance embedding. The dual embedding leads to generated images that better match the scene graph, have higher visual quality, and support more complex scene graphs. In addition, the embedding scheme supports multiple and diverse output images per scene graph, which can be further controlled by the user. We demonstrate two modes of per-object control: (i) importing elements from other images, and (ii) navigation in the object space, by selecting an appearance archetype. Our code is publicly available at https://www.github.com/ashual/scene_generation