no code implementations • ECCV 2020 • Xuchong Qiu, Yang Xiao, Chaohui Wang, Renaud Marlet
Inference & Application","We formalize concepts around geometric occlusion in 2D images (i. e., ignoring semantics), and propose a novel unified formulation of both occlusion boundaries and occlusion orientations via a pixel-pair occlusion relation.
no code implementations • 27 Aug 2024 • Lintao XU, Chaohui Wang
To this end, we have developed an efficient tool, named Mesh2OB, for the automatic generation of 2D images together with their ground-truth OBs, using which we have constructed a synthetic benchmark, named OB-FUTURE.
1 code implementation • 23 Jul 2020 • Xuchong Qiu, Yang Xiao, Chaohui Wang, Renaud Marlet
The former provides a way to generate large-scale accurate occlusion datasets while, based on the latter, we propose a novel method for task-independent pixel-level occlusion relationship estimation from single images.
1 code implementation • 21 Jan 2019 • Yanwu Xu, Mingming Gong, Tongliang Liu, Kayhan Batmanghelich, Chaohui Wang
In recent years, the learned local descriptors have outperformed handcrafted ones by a large margin, due to the powerful deep convolutional neural network architectures such as L2-Net [1] and triplet based metric learning [2].
1 code implementation • CVPR 2019 • Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, Kun Zhang, DaCheng Tao
Unsupervised domain mapping aims to learn a function to translate domain X to Y by a function GXY in the absence of paired examples.
no code implementations • 19 Jun 2018 • Huan Fu, Mingming Gong, Chaohui Wang, DaCheng Tao
In the proposed networks, different levels of features at each spatial location are adaptively re-weighted according to the local structure and surrounding contextual information before aggregation.
5 code implementations • CVPR 2018 • Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, DaCheng Tao
These methods model depth estimation as a regression problem and train the regression networks by minimizing mean squared error, which suffers from slow convergence and unsatisfactory local solutions.
Ranked #13 on
Depth Estimation
on NYU-Depth V2
no code implementations • 28 Aug 2017 • Huan Fu, Mingming Gong, Chaohui Wang, DaCheng Tao
However, we find that training a network to predict a high spatial resolution continuous depth map often suffers from poor local solutions.
2 code implementations • 28 Jun 2017 • Chaoyue Wang, Chang Xu, Chaohui Wang, DaCheng Tao
The proposed PAN consists of two feed-forward convolutional neural networks (CNNs), the image transformation network T and the discriminative network D. Through combining the generative adversarial loss and the proposed perceptual adversarial loss, these two networks can be trained alternately to solve image-to-image transformation tasks.
no code implementations • International Joint Conference on Artificial Intelligence 2017 • Chaoyue Wang, Chaohui Wang, Chang Xu, DaCheng Tao
The whole framework consists of a disentangling network, a generative network, a tag mapping net, and a discriminative network, which are trained jointly based on a given set of images that are complete/partially tagged(i. e., supervised/semi-supervised setting).
no code implementations • CVPR 2016 • Huan Fu, Chaohui Wang, DaCheng Tao, Michael J. Black
Occlusion boundaries contain rich perceptual information about the underlying scene structure.
no code implementations • ICCV 2015 • Zhou Ren, Chaohui Wang, Alan L. Yuille
In this paper, we are interested in enhancing the expressivity and robustness of part-based models for object representation, in the common scenario where the training data are based on 2D images.
no code implementations • CVPR 2015 • Zhibin Hong, Zhe Chen, Chaohui Wang, Xue Mei, Danil Prokhorov, DaCheng Tao
Variations in the appearance of a tracked object, such as changes in geometry/photometry, camera viewpoint, illumination, or partial occlusion, pose a major challenge to object tracking.
no code implementations • CVPR 2013 • Yun Zeng, Chaohui Wang, Stefano Soatto, Shing-Tung Yau
This paper introduces an efficient approach to integrating non-local statistics into the higher-order Markov Random Fields (MRFs) framework.