MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination

by   Shengyu Zhang, et al.

In this paper, we investigate the problem of text-to-pedestrian synthesis, which has many potential applications in art, design, and video surveillance. Existing methods for text-to-bird/flower synthesis are still far from solving this fine-grained image generation problem, due to the complex structure and heterogeneous appearance that the pedestrians naturally take on. To this end, we propose the Multi-Grained Discrimination enhanced Generative Adversarial Network, that capitalizes a human-part-based Discriminator (HPD) and a self-cross-attended (SCA) global Discriminator in order to capture the coherence of the complex body structure. A fined-grained word-level attention mechanism is employed in the HPD module to enforce diversified appearance and vivid details. In addition, two pedestrian generation metrics, named Pose Score and Pose Variance, are devised to evaluate the generation quality and diversity, respectively. We conduct extensive experiments and ablation studies on the caption-annotated pedestrian dataset, CUHK Person Description Dataset. The substantial improvement over the various metrics demonstrates the efficacy of MGD-GAN on the text-to-pedestrian synthesis scenario.


page 1

page 3

page 6

page 7


Fine-grained Semantic Constraint in Image Synthesis

In this paper, we propose a multi-stage and high-resolution model for im...

HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generation

Text-driven person image generation is an emerging and challenging task ...

Object-driven Text-to-Image Synthesis via Adversarial Training

In this paper, we propose Object-driven Attentive Generative Adversarial...

Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator

Automatic font generation remains a challenging research issue due to th...

Towards Using Clothes Style Transfer for Scenario-aware Person Video Generation

Clothes style transfer for person video generation is a challenging task...

Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis

The advent of data-driven technology solutions is accompanied by an incr...

Please sign up or login with your details

Forgot password? Click here to reset