paper-with-me

홈 › Papers

SymmNet: A Symmetric Convolutional Neural Network for Occlusion Detection

2018-07-03 · Ang Li, Zejian yuan

Detecting the occlusion from stereo images or video frames is important to many computer vision applications. Previous efforts focus on bundling it with the computation of disparity or optical flow, leading to a chicken-and-egg problem. In this paper, we leverage convolutional neural network to liberate the occlusion detection task from the interleaved, traditional calculation framework. We propose a Symmetric Network (SymmNet) to directly exploit information from an image pair, without estimating disparity or motion in advance. The proposed network is structurally left-right symmetric to learn the binocular occlusion simultaneously, aimed at jointly improving both results. The comprehensive experiments show that our model achieves state-of-the-art results on detecting the stereo and motion occlusion.

📄 PDF Abstract BibTeX arXiv:1807.00959

Code (0)

등록된 구현이 없습니다.

Tasks

Optical Flow Estimation

Similar Papers 제목 키워드 기반

AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks

2021-04-15 · Haojin Yang, Zhen Shen, Yucheng Zhao

Deep convolutional neural networks (CNN) have achieved astonishing results in a large variety of applications. However, using these models on mobile or embedded devices is difficult due to the limited memory and computat…

Image Classification

Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice

2020-02-20 · Yabin Zhang, Bin Deng, Hui Tang, Lei Zhang 외

In this paper, we study the formalism of unsupervised multi-class domain adaptation (multi-class UDA), which underlies a few recent algorithms whose learning objectives are only motivated empirically. Multi-Class Scoring…

Domain AdaptationMulti-class Classification

Tracking Human Pose by Tracking Symmetric Parts

2013-06-01 · CVPR 2013 6 · Varun Ramakrishna, Takeo Kanade, Yaser Sheikh

The human body is structurally symmetric. Tracking by detection approaches for human pose suffer from double counting, where the same image evidence is used to explain two separate but symmetric parts, such as the left a…

Action RecognitionPose EstimationTemporal Action Localization

Occlusion Edge Detection in RGB-D Frames using Deep Convolutional Networks

2014-12-22 · Soumik Sarkar, Vivek Venugopalan, Kishore Reddy, Michael Giering 외

Occlusion edges in images which correspond to range discontinuity in the scene from the point of view of the observer are an important prerequisite for many vision and mobile robot tasks. Although they can be extracted f…

Edge Detection

3D Pose Detection in Videos: Focusing on Occlusion

2020-06-24 · Justin Wang, Edward Xu, Kangrui Xue, Lukasz Kidzinski

In this work, we build upon existing methods for occlusion-aware 3D pose detection in videos. We implement a two stage architecture that consists of the stacked hourglass network to produce 2D pose predictions, which are…

Position