# Image-to-Image Translation with Text Guidance

Source: [Image-to-Image Translation with Text Guidance](<https://www.sota2.com/research/paper/68fa67091e209131cea13fd4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:05:19.802Z

Authors: Bowen Li, Xiaojuan Qi, Philip H. S. Torr, Thomas Lukasiewicz

Published: 2020-02-12T21:09:15.000Z

## Abstract

The goal of this paper is to embed controllable factors, i.e., natural language descriptions, into image-to-image translation with generative adversarial networks, which allows text descriptions to determine the visual attributes of synthetic images. We propose four key components: (1) the implementation of part-of-speech tagging to filter out non-semantic words in the given description, (2) the adoption of an affine combination module to effectively fuse different modality text and image features, (3) a novel refined multi-stage architecture to strengthen the differential ability of discriminators and the rectification ability of generators, and (4) a new structure loss to further improve discriminators to better distinguish real and synthetic images. Extensive experiments on the COCO dataset demonstrate that our method has a superior performance on both visual realism and semantic consistency with given descriptions.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2002.05235>)

[PDF](<https://arxiv.org/pdf/2002.05235.pdf>)