Carol O'Sullivan — accepted AI-conference papers

2024

Synthesizing Environment-Specific People in Photographs

Mirela Ostrek*, Carol O'Sullivan, Michael J. Black, Justus Thies

ECCV 2024poster

"We present ESP, a novel method for context-aware full-body generation, that enables photo-realistic synthesis and inpainting of people wearing clothing that is semantically appropriate for the scene depicted in an input photograph. ESP is conditioned on a 2D pose and contextual cues that are extrac…

Cited by 0 Source ↗PDF ↗Scholar ↗

2016

HI Robot: Human intention-aware robot planning for safe and efficient navigation in crowds

Chonhyon Park, Jan Ondřej, Max Gilbert, Kyle Freeman, Carol O'Sullivan

IROS 2016poster

We present an algorithmic framework for the early classification of human intentions, and use it to accurately predict future human motions when planning the path of a robot in an environment that is shared with humans. During an off-line learning phase, a classifier that can recognize when a human…

Cited by 34 Source ↗Scholar ↗