Generation of Synthetic Images for Pedestrian Detection Using a Sequence of GANs
This proof-of-concept work addresses dataset creation for pedestrian detection, but it is incremental as it combines existing GANs in a new way.
The paper tackles the problem of manual annotation effort for datasets by proposing a novel pipeline using three distinct GANs to generate synthetic images for pedestrian detection, resulting in detection results that substantially surpass the baseline.
Creating annotated datasets demands a substantial amount of manual effort. In this proof-of-concept work, we address this issue by proposing a novel image generation pipeline. The pipeline consists of three distinct generative adversarial networks (previously published), combined in a novel way to augment a dataset for pedestrian detection. Despite the fact that the generated images are not always visually pleasant to the human eye, our detection benchmark reveals that the results substantially surpass the baseline. The presented proof-of-concept work was done in 2020 and is now published as a technical report after a three years retention period.