Search Results for author: Hongbin Zha

Found 24 papers, 4 papers with code

Active Neural Mapping

no code implementations30 Aug 2023 Zike Yan, Haoxiang Yang, Hongbin Zha

We address the problem of active mapping with a continually-learned neural scene representation, namely Active Neural Mapping.

ECT: Fine-grained Edge Detection with Learned Cause Tokens

1 code implementation6 Aug 2023 Shaocong Xu, Xiaoxue Chen, Yuhang Zheng, Guyue Zhou, Yurong Chen, Hongbin Zha, Hao Zhao

To address these three issues, we propose a two-stage transformer-based network sequentially predicting generic edges and fine-grained edges, which has a global receptive field thanks to the attention mechanism.

Edge Detection

SC-wLS: Towards Interpretable Feed-forward Camera Re-localization

1 code implementation23 Oct 2022 Xin Wu, Hao Zhao, Shunkai Li, Yingdian Cao, Hongbin Zha

Visual re-localization aims to recover camera poses in a known environment, which is vital for applications like robotics or augmented reality.


Transferable End-to-end Room Layout Estimation via Implicit Encoding

no code implementations21 Dec 2021 Hao Zhao, Rene Ranftl, Yurong Chen, Hongbin Zha

Here we propose an end-to-end method that directly predicts parametric layouts from an input panorama image.

Room Layout Estimation

Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observations

no code implementations ICCV 2021 Zike Yan, Yuxin Tian, Xuesong Shi, Ping Guo, Peng Wang, Hongbin Zha

We introduce an experience replay approach to tackle an exemplary task of continual neural mapping: approximating a continuous signed distance function (SDF) from sequential depth images as a scene geometry representation.

Continual Learning

Online Learning of a Probabilistic and Adaptive Scene Representation

no code implementations CVPR 2021 Zike Yan, Xin Wang, Hongbin Zha

Constructing and maintaining a consistent scene model on-the-fly is the core task for online spatial perception, interpretation, and action.

Line Flow based SLAM

no code implementations21 Sep 2020 Qiuyuan Wang, Zike Yan, Junqiu Wang, Fei Xue, Wei Ma, Hongbin Zha

To address these problems, we leverage a line flow to encode the coherence of line segment observations of the same 3D line along the temporal dimension, which has been neglected in prior SLAM systems.

Self-Supervised Deep Visual Odometry with Online Adaptation

no code implementations CVPR 2020 Shunkai Li, Xin Wang, Yingdian Cao, Fei Xue, Zike Yan, Hongbin Zha

In this paper, we propose an online meta-learning algorithm to enable VO networks to continuously adapt to new environments in a self-supervised manner.

Meta-Learning Visual Odometry

Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry

no code implementations ICCV 2019 Shunkai Li, Fei Xue, Xin Wang, Zike Yan, Hongbin Zha

As single-view depth estimation is an ill-posed problem, and photometric loss is incapable of discriminating distortion artifacts of warped images, the estimated depth is vague and pose is inaccurate.

Depth Estimation Image Generation +2

Guided Feature Selection for Deep Visual Odometry

no code implementations25 Nov 2018 Fei Xue, Qiuyuan Wang, Xin Wang, Wei Dong, Junqiu Wang, Hongbin Zha

We present a novel end-to-end visual odometry architecture with guided feature selection based on deep convolutional recurrent neural networks.

feature selection Monocular Visual Odometry +1

Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining

no code implementations ECCV 2018 Xia Li, Jianlong Wu, Zhouchen Lin, Hong Liu, Hongbin Zha

In heavy rain, rain streaks have various directions and shapes, which can be regarded as the accumulation of multiple rain streak layers.

Single Image Deraining

Essential Tensor Learning for Multi-view Spectral Clustering

no code implementations10 Jul 2018 Jianlong Wu, Zhouchen Lin, Hongbin Zha

In this paper, we focus on the Markov chain based spectral clustering method and propose a novel essential tensor learning method to explore the high order correlations for multi-view representation.


A Unified Convex Surrogate for the Schatten-$p$ Norm

no code implementations25 Nov 2016 Chen Xu, Zhouchen Lin, Hongbin Zha

In this paper, we show that for any $p$, $p_1$, and $p_2 >0$ satisfying $1/p=1/p_1+1/p_2$, there is an equivalence between the Schatten-$p$ norm of one matrix and the Schatten-$p_1$ and the Schatten-$p_2$ norms of its two factor matrices.

Matrix Completion

Camera Calibration From Periodic Motion of a Pedestrian

no code implementations CVPR 2016 Shiyao Huang, Xianghua Ying, Jiangpeng Rong, Zeyu Shang, Hongbin Zha

Camera calibration directly from image sequences of a pedestrian without using any calibration object is a really challenging task and should be well solved in computer vision, especially in visual surveillance.

Camera Calibration

Relaxed Majorization-Minimization for Non-smooth and Non-convex Optimization

no code implementations25 Nov 2015 Chen Xu, Zhouchen Lin, Zhenyu Zhao, Hongbin Zha

We propose a new majorization-minimization (MM) method for non-smooth and non-convex programs, which is general enough to include the existing MM methods.

Cannot find the paper you are looking for? You can Submit a new open access paper.