Log In Sign Up

Context-Aware Layout to Image Generation with Enhanced Object Appearance

by   Sen He, et al.

A layout to image (L2I) generation model aims to generate a complicated image containing multiple objects (things) against natural background (stuff), conditioned on a given layout. Built upon the recent advances in generative adversarial networks (GANs), existing L2I models have made great progress. However, a close inspection of their generated images reveals two major limitations: (1) the object-to-object as well as object-to-stuff relations are often broken and (2) each object's appearance is typically distorted lacking the key defining characteristics associated with the object class. We argue that these are caused by the lack of context-aware object and stuff feature encoding in their generators, and location-sensitive appearance representation in their discriminators. To address these limitations, two new modules are proposed in this work. First, a context-aware feature transformation module is introduced in the generator to ensure that the generated feature encoding of either object or stuff is aware of other co-existing objects/stuff in the scene. Second, instead of feeding location-insensitive image features to the discriminator, we use the Gram matrix computed from the feature maps of the generated object images to preserve location-sensitive information, resulting in much enhanced object appearance. Extensive experiments show that the proposed method achieves state-of-the-art performance on the COCO-Thing-Stuff and Visual Genome benchmarks.


page 1

page 6

page 7

page 8


Exploiting Relationship for Complex-scene Image Generation

The significant progress on Generative Adversarial Networks (GANs) has f...

Text to Image Generation with Semantic-Spatial Aware GAN

A text to image generation (T2I) model aims to generate photo-realistic ...

Learning a Layout Transfer Network for Context Aware Object Detection

We present a context aware object detection method based on a retrieve-a...

Context-Aware Synthesis and Placement of Object Instances

Learning to insert an object instance into an image in a semantically co...

Context-Aware Synthesis and Placement ofObject Instances

Learning to insert an object instance into an image in a semantically co...

Image Synthesis From Reconfigurable Layout and Style

Despite remarkable recent progress on both unconditional and conditional...

Person-in-Context Synthesiswith Compositional Structural Space

Despite significant progress, controlled generation of complex images wi...