Secrets in Computing Optical Flow by Convolutional Networks
نویسنده
چکیده
Convolutional neural networks (CNNs) have been widely used over many areas in compute vision. Especially in classification. Recently, FlowNet and several works on optical estimation using CNNs shows the potential ability of CNNs in doing per-pixel regression. We proposed several CNNs network architectures that can estimate optical flow, and fully unveiled the intrinsic different between these structures.
منابع مشابه
Deep Tracking: Visual Tracking Using Deep Convolutional Networks
In this paper, we study discriminatively trained deep convolutional networks for the task of visual tracking. Our tracker utilizes both motion and appearance features extracted from a pre-trained dual stream deep convolution network. By using optical flow and deep networks to implement a dual appearance and motion stream to inform tracking, our tracker outperforms current state of the art track...
متن کاملConvolutional Neural Networks for Video Frame Interpolation
Video frame interpolation has applications in video compression as well as up-sampling to higher frame rates. However, it is a challenging task, especially when objects in the scene are moving in different ways. The current state-of-the-art methods use optical flow to account for motion in a scene, but computing optical flow robustly is still a difficult process, which can lead to artifacts in ...
متن کاملIntegration of Deep Learning Algorithms and Bilateral Filters with the Purpose of Building Extraction from Mono Optical Aerial Imagery
The problem of extracting the building from mono optical aerial imagery with high spatial resolution is always considered as an important challenge to prepare the maps. The goal of the current research is to take advantage of the semantic segmentation of mono optical aerial imagery to extract the building which is realized based on the combination of deep convolutional neural networks (DCNN) an...
متن کاملDeep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks
This paper discusses the problem of tracking from a deep learning approach. This experiment takes cues from how the brain is modeled to create deep convolutional networks that mimic how the human brain tracks objects. By using optical flow and deep networks to implement a dual appearance and motion stream, our tracker outperforms current state of the art methods.
متن کاملSemi-Supervised Learning for Optical Flow with Generative Adversarial Networks
Convolutional neural networks (CNNs) have recently been applied to the optical flow estimation problem. As training the CNNs requires sufficiently large amounts of labeled data, existing approaches resort to synthetic, unrealistic datasets. On the other hand, unsupervised methods are capable of leveraging real-world videos for training where the ground truth flow fields are not available. These...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1710.01462 شماره
صفحات -
تاریخ انتشار 2017