Optical Flow

DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework
Optical flow estimation is essential for video processing tasks, such as restoration and action recognition. The quality of videos is …
Henrique Morimitsu, Xiaobin Zhu, Roberto M. Cesar-Jr., Xiangyang Ji, Xu-Cheng Yin
PDF Cite Code Dataset
DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework
CVPR 2025 paper
Our paper “DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework” has been accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (Jun 11-15, 2025, Nashville, USA).
Mar 20, 2025
RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation
Extracting motion information from videos with optical flow estimation is vital in multiple practical robot applications. Current …
Henrique Morimitsu, Xiaobin Zhu, Roberto M. Cesar-Jr., Xiangyang Ji, Xu-Cheng Yin
PDF Cite Code Video
RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation
ICRA 2024 paper
Our paper “RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation” has been accepted to the IEEE International Conference on Robotics and Automation (May 13-17, 2024, Yokohama, Japan).
Mar 7, 2024
Recurrent Partial Kernel Network for Efficient Optical Flow Estimation
Optical flow estimation is a challenging task consisting of predicting per-pixel motion vectors between images. Recent methods have …
Henrique Morimitsu, Xiaobin Zhu, Xiangyang Ji, Xu-Cheng Yin
PDF Cite Code Video DOI
Recurrent Partial Kernel Network for Efficient Optical Flow Estimation
AAAI 2024 paper
Our paper “Recurrent Partial Kernel Network for Efficient Optical Flow Estimation” has been accepted to The 38th Annual AAAI Conference on Artificial Intelligence (February 20-27, 2024, Vancouver, Canada).
Dec 14, 2023
DAISY GPU
An implementation of the DAISY descriptor using deep learning libraries (PyTorch and Tensorflow).
PTLFlow
PyTorch Lightning platform for training and testing state-of-the-art Optical Flow models.
SIFT-Flow GPU
An implementation of the SIFT-Flow descriptor using PyTorch.
A Unified Framework for Piecewise Semantic Reconstruction in Dynamic Scenes via Exploiting Superpixel Relations
This paper presents a novel framework for dense piecewise semantic reconstruction in dynamic scenes containing complex background and …
Yan Di, Henrique Morimitsu, Zhiqiang Lou, Xiangyang Ji
PDF Cite DOI
A Unified Framework for Piecewise Semantic Reconstruction in Dynamic Scenes via Exploiting Superpixel Relations