Towards Better Adversarial Synthesis of Human Images from Text

TL;DR

This paper introduces a method for generating multiple 3D human meshes from text descriptions, improving the realism and interaction modeling of human figures in synthesized images.

Contribution

It presents a novel approach that synthesizes 3D human shapes from text and integrates these shapes into image synthesis to enhance realism.

Findings

Effective generation of diverse 3D human meshes from text

Improved realism in human shape synthesis within images

Captures scene dynamics and interactions from textual descriptions

Abstract

This paper proposes an approach that generates multiple 3D human meshes from text. The human shapes are represented by 3D meshes based on the SMPL model. The model's performance is evaluated on the COCO dataset, which contains challenging human shapes and intricate interactions between individuals. The model is able to capture the dynamics of the scene and the interactions between individuals based on text. We further show how using such a shape as input to image synthesis frameworks helps to constrain the network to synthesize humans with realistic human shapes.