230 citations · 1.1k across the 84 of their papers we have counts for
15 papers · 1 filter
Uncertainty-Aware Deep Calibrated Salient Object Detection
Jing Zhang, Yuchao Dai, Xin Yu +3
Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy. However, those methods overlook the gap between network ac…
Depth Completion using Piecewise Planar Model
Yiran Zhong, Yuchao Dai, Hongdong Li
A depth map can be represented by a set of learned bases and can be efficiently solved in a closed form solution. However, one issue with this method is that it may create artifact…
Efficient Depth Completion Using Learned Bases
Yiran Zhong, Yuchao Dai, Hongdong Li
In this paper, we propose a new global geometry constraint for depth completion. By assuming depth maps often lay on low dimensional subspaces, a dense depth map can be approximate…
Displacement-Invariant Cost Computation for Efficient Stereo Matching
Yiran Zhong, Charles Loop, Wonmin Byeon +7
Although deep learning-based methods have dominated stereo matching leaderboards by yielding unprecedented disparity accuracy, their inference time is typically slow, on the order…
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
Jianyuan Wang, Yiran Zhong, Yuchao Dai +3
Learning matching costs has been shown to be critical to the success of the state-of-the-art deep stereo matching methods, in which 3D convolutions are applied on a 4D feature volu…
Hierarchical Neural Architecture Search for Deep Stereo Matching
Xuelian Cheng, Yiran Zhong, Mehrtash Harandi +5
To reduce the human efforts in neural network design, Neural Architecture Search (NAS) has been applied with remarkable success to various high-level vision tasks such as classific…
Novel View Synthesis from only a 6-DoF Camera Pose by Two-stage Networks
Xiang Guo, Bo Li, Yuchao Dai +2
Novel view synthesis is a challenging problem in computer vision and robotics. Different from the existing works, which need the reference images or 3D models of the scene to gener…
PRAFlow_RVC: Pyramid Recurrent All-Pairs Field Transforms for Optical Flow Estimation in Robust Vision Challenge 2020
Zhexiong Wan, Yuxin Mao, Yuchao Dai
Optical flow estimation is an important computer vision task, which aims at estimating the dense correspondences between two frames. RAFT (Recurrent All Pairs Field Transforms) cur…
Uncertainty Inspired RGB-D Saliency Detection
Jing Zhang, Deng-Ping Fan, Yuchao Dai +4
We propose the first stochastic framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection models tr…
Dense Non-Rigid Structure from Motion: A Manifold Viewpoint
Suryansh Kumar, Luc Van Gool, Carlos E. P. de Oliveira +3
Non-Rigid Structure-from-Motion (NRSfM) problem aims to recover 3D geometry of a deforming object from its 2D feature correspondences across multiple frames. Classical approaches t…
Relative Pose Estimation for Stereo Rolling Shutter Cameras
Ke Wang, Bin Fan, Yuchao Dai
In this paper, we present a novel linear algorithm to estimate the 6 DoF relative pose from consecutive frames of stereo rolling shutter (RS) cameras. Our method is derived based o…
Channel Attention based Iterative Residual Learning for Depth Map Super-Resolution
Xibin Song, Yuchao Dai, Dingfu Zhou +4
Despite the remarkable progresses made in deep-learning based depth map super-resolution (DSR), how to tackle real-world degradation in low-resolution (LR) depth maps remains a maj…
PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching
Zhelun Shen, Yuchao Dai, Xibin Song +3
Existing deep learning based stereo matching methods either focus on achieving optimal performances on the target dataset while with poor generalization for other datasets or focus…
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
Jing Zhang, Deng-Ping Fan, Yuchao Dai +4
In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detecti…
Weakly-Supervised Salient Object Detection via Scribble Annotations
Jing Zhang, Xin Yu, Aixuan Li +3
Compared with laborious pixel-wise dense labeling, it is much easier to label data by scribbles, which only costs 12 seconds to label one image. However, using scribble label…