Roberto M. Cesar — accepted AI-conference papers

2025

DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework

Henrique Morimitsu, Xiaobin Zhu, Roberto M. Cesar, Xiangyang Ji, Xu-Cheng Yin

CVPR 2025poster

Optical flow estimation is essential for video processing tasks, such as restoration and action recognition. The quality of videos is constantly increasing, with current standards reaching 8K resolution. However, optical flow methods are usually designed for low resolution and do not generalize to l…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation

Henrique Morimitsu, Xiaobin Zhu, Roberto M. Cesar, Xiangyang Ji, Xu-Cheng Yin

ICRA 2024poster

Extracting motion information from videos with optical flow estimation is vital in multiple practical robot applications. Current optical flow approaches show remarkable accuracy, but top-performing methods have high computational costs and are unsuitable for embedded devices. Although some previous…

Cited by 8 Source ↗code ↗Scholar ↗