Specifying Object Attributes and Relations in Interactive Scene Generation

ICCV 2019  ·  Oron Ashual, Lior Wolf ·

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

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Layout-to-Image Generation COCO-Stuff 128x128 SOARISG FID 59.5 # 5
Inception Score 12.5 # 5
SceneFID 33.46 # 3
Layout-to-Image Generation COCO-Stuff 64x64 SOARISG FID 48.7 # 4
Inception Score 10.3 # 2


No methods listed for this paper. Add relevant methods here