Iterative residual refinement for joint optical flow and occlusion estimation
Deep learning approaches to optical flow estimation have seen rapid progress over the
recent years. One common trait of many networks is that they refine an initial flow estimate …
recent years. One common trait of many networks is that they refine an initial flow estimate …
Occlusion aware unsupervised learning of optical flow
It has been recently shown that a convolutional neural network can learn optical flow
estimation with unsuper-vised learning. However, the performance of the unsuper-vised …
estimation with unsuper-vised learning. However, the performance of the unsuper-vised …
Optical flow modeling and computation: A survey
Optical flow estimation is one of the oldest and still most active research domains in
computer vision. In 35 years, many methodological concepts have been introduced and …
computer vision. In 35 years, many methodological concepts have been introduced and …
Mirrorflow: Exploiting symmetries in joint optical flow and occlusion estimation
Optical flow estimation is one of the most studied problems in computer vision, yet recent
benchmark datasets continue to reveal problem areas of today's approaches. Occlusions …
benchmark datasets continue to reveal problem areas of today's approaches. Occlusions …
Patch-based video denoising with optical flow estimation
A novel image sequence denoising algorithm is presented. The proposed approach takes
advantage of the self-similarity and redundancy of adjacent frames. The algorithm is inspired …
advantage of the self-similarity and redundancy of adjacent frames. The algorithm is inspired …
A level set based fractional order variational model for motion estimation in application oriented spectrum
In recent years, motion estimation has become prominent in the field of computer vision. This
is due to its applications in various domains such as object detection, video surveillance …
is due to its applications in various domains such as object detection, video surveillance …
Rethinking optical flow methods for micro-expression spotting
Y Zhao, X Tong, Z Zhu, J Sheng, L Dai, L Xu… - Proceedings of the 30th …, 2022 - dl.acm.org
Micro-expressions (MEs) spotting is popular in some fields, for example, criminal
investigation and business communication. But it is still a challenging task to spot the onset …
investigation and business communication. But it is still a challenging task to spot the onset …
Hand-held video deblurring via efficient fourier aggregation
Videos captured with hand-held cameras often suffer from a significant amount of blur,
mainly caused by the inevitable natural tremor of the photographer's hand. In this work, we …
mainly caused by the inevitable natural tremor of the photographer's hand. In this work, we …
Crowd event detection on optical flow manifolds
Analyzing crowd events in a video is key to understanding the behavioral characteristics of
people (humans). Detecting crowd events in videos is challenging because of articulated …
people (humans). Detecting crowd events in videos is challenging because of articulated …
A nonlinear modeling of fractional order based variational model in optical flow estimation
In this paper, a nonlinear fractional order variational (NFOV) model is introduced to estimate
the optical flow. In particular, the presented model can be scaled to the existing integer order …
the optical flow. In particular, the presented model can be scaled to the existing integer order …