Gaflow: Incorporating gaussian attention into optical flow

A Luo, F Yang, X Li, L Nie, C Lin… - Proceedings of the …, 2023 - openaccess.thecvf.com
Optical flow, or the estimation of motion fields from image sequences, is one of the
fundamental problems in computer vision. Unlike most pixel-wise tasks that aim at achieving …

Supervised homography learning with realistic dataset generation

H Jiang, H Li, S Han, H Fan… - Proceedings of the …, 2023 - openaccess.thecvf.com
In this paper, we propose an iterative framework, which consists of two phases: a generation
phase and a training phase, to generate realistic training data and yield a supervised …

Dmhomo: Learning homography with diffusion models

H Li, H Jiang, A Luo, P Tan, H Fan, B Zeng… - ACM Transactions on …, 2024 - dl.acm.org
Supervised homography estimation methods face a challenge due to the lack of adequate
labeled training data. To address this issue, we propose DMHomo, a diffusion model-based …

Single image rolling shutter removal with diffusion models

Z Yang, H Li, M Hong, B Zeng, S Liu - ar** Deep Homography With Video Coding
Y Liu, H Li, S Liu, B Zeng - … on Circuits and Systems for Video …, 2024 - ieeexplore.ieee.org
Homography estimation is a fundamental task in computer vision with applications in diverse
fields. Recent advances in deep learning have improved homography estimation …

Blind 3D Video Stabilization with Spatio-Temporally Varying Motion Blur

H Li, W Wang, X Wang, X Yuan, X Xu - ACM Transactions on Multimedia …, 2024 - dl.acm.org
Video stabilization is a challenging task that attempts to compensate for the overall frame
shake during video acquisition. Existing three-dimensional video stabilization methods aim …

[PDF][PDF] Robust Unsupervised Optical Flow Under Low-Visibility Conditions

L Long, T Liu, R Laganière, J Lang - vcad-workshop.github.io
Although state-of-the-art unsupervised optical flow methods achieve impressive results in
clean scenes, they still struggle under lowvisibility weather and illumination. However …