Timezone: »

 
Poster
PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
Yikang LI · Tao Ma · Yeqi Bai · Nan Duan · Sining Wei · Xiaogang Wang

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #131
in Deep Learning -- Generative Models »

Despite some exciting progress on high-quality image generation from structured (scene graphs) or free-form (sentences) descriptions, most of them only guarantee the image-level semantical consistency, i.e. the generated image matching the semantic meaning of the description. They still lack the investigations on synthesizing the images in a more controllable way, like finely manipulating the visual appearance of every object. Therefore, to generate the images with preferred objects and rich interactions, we propose a semi-parametric method, PasteGAN, for generating the image from the scene graph and the image crops, where spatial arrangements of the objects and their pair-wise relationships are defined by the scene graph and the object appearances are determined by the given object crops. To enhance the interactions of the objects in the output, we design a Crop Refining Network and an Object-Image Fuser to embed the objects as well as their relationships into one map. Multiple losses work collaboratively to guarantee the generated images highly respecting the crops and complying with the scene graphs while maintaining excellent image quality. A crop selector is also proposed to pick the most-compatible crops from our external object tank by encoding the interactions around the objects in the scene graph if the crops are not provided. Evaluated on Visual Genome and COCO-Stuff dataset, our proposed method significantly outperforms the SOTA methods on Inception Score, Diversity Score and Fréchet Inception Distance. Extensive experiments also demonstrate our method’s ability to generate complex and diverse images with given objects. The code is available at https://github.com/yikang-li/PasteGAN.

Keywords: Generative Models · Deep Learning · Applications -> Computer Vision; Applications -> Visual Scene Analysis and Interpretation; Deep Learning · Adversarial Network
[ Paper]  [ Poster] 

Author Information

Yikang LI (The Chinese University of Hong Kong; Sensetime)
Tao Ma (Northwestern Polytechnical University)
Yeqi Bai (Nanyang Technological University)
Nan Duan (Microsoft Research Asia)
Sining Wei (Microsoft Research)
Xiaogang Wang (The Chinese University of Hong Kong)

More from the Same Authors