CosmicMan: A Text-to-Image Foundation Model for Humans

no code implementations • CVPR 2024 • Shikai Li, Jianglin Fu, Kaiyuan Liu, Wentao Wang, Kwan-Yee Lin, Wayne Wu

We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images.

UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation

1 code implementation • ICCV 2023 • Jianglin Fu, Shikai Li, Yuming Jiang, Kwan-Yee Lin, Wayne Wu, Ziwei Liu

A holistic human dataset inevitably has insufficient and low-resolution information on local parts.

StyleGAN-Human: A Data-Centric Odyssey of Human Generation

4 code implementations • 25 Apr 2022 • Jianglin Fu, Shikai Li, Yuming Jiang, Kwan-Yee Lin, Chen Qian, Chen Change Loy, Wayne Wu, Ziwei Liu

In addition, a model zoo and human editing applications are demonstrated to facilitate future research in the community.

Image Generation

Datasets for Face and Object Detection in Fisheye Images

no code implementations • 27 Jun 2019 • Jianglin Fu, Ivan V. Bajic, Rodney G. Vaughan

We present two new fisheye image datasets for training face and object detection models: VOC-360 and Wider-360.

Face Detection Object +3

FDDB-360: Face Detection in 360-degree Fisheye Images

no code implementations • 7 Feb 2019 • Jianglin Fu, Saeed Ranjbar Alvar, Ivan V. Bajic, Rodney G. Vaughan

360-degree cameras offer the possibility to cover a large area, for example an entire room, without using multiple distributed vision sensors.

Face Detection