Search Results for author: Haojie Liu

Found 17 papers, 3 papers with code

Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification

no code implementations11 Apr 2022 Haojie Liu, Daoxun Xia, Wei Jiang, Chao Xu

In order to mitigate the impact of large modality discrepancy existing in heterogeneous images, previous methods attempt to apply generative adversarial network (GAN) to generate the modality-consisitent data.

Person Re-Identification

End-to-end Neural Video Coding Using a Compound Spatiotemporal Representation

no code implementations5 Aug 2021 Haojie Liu, Ming Lu, Zhiqi Chen, Xun Cao, Zhan Ma, Yao Wang

We further design a one-to-many decoder pipeline to generate multiple predictions from the CSTR, including vector-based resampling, adaptive kernel-based resampling, compensation mode selection maps and texture enhancements, and combines them adaptively to achieve more accurate inter prediction.

Motion Compensation MS-SSIM +3

PDWN: Pyramid Deformable Warping Network for Video Interpolation

no code implementations4 Apr 2021 Zhiqi Chen, Ran Wang, Haojie Liu, Yao Wang

At the finest scale, the two warped frames are adaptively blended to generate the middle frame.

Optical Flow Estimation

SFANet: A Spectrum-aware Feature Augmentation Network for Visible-Infrared Person Re-Identification

no code implementations24 Feb 2021 Haojie Liu, Shun Ma, Daoxun Xia, Shaozi Li

In feature-level, we improve the conventional two-stream network through balancing the number of specific and sharable convolutional blocks, which preserve the spatial structure information of features.

Person Re-Identification

Neural Video Coding using Multiscale Motion Compensation and Spatiotemporal Context Model

no code implementations9 Jul 2020 Haojie Liu, Ming Lu, Zhan Ma, Fan Wang, Zhihuang Xie, Xun Cao, Yao Wang

Over the past two decades, traditional block-based video coding has made remarkable progress and spawned a series of well-known standards such as MPEG-4, H. 264/AVC and H. 265/HEVC.

Motion Compensation MS-SSIM +2

Pseudo-LiDAR Point Cloud Interpolation Based on 3D Motion Representation and Spatial Supervision

no code implementations20 Jun 2020 Haojie Liu, Kang Liao, Chunyu Lin, Yao Zhao, Yulan Guo

Pseudo-LiDAR point cloud interpolation is a novel and challenging task in the field of autonomous driving, which aims to address the frequency mismatching problem between camera and LiDAR.

Autonomous Driving Optical Flow Estimation

Object-Based Image Coding: A Learning-Driven Revisit

no code implementations18 Mar 2020 Qi Xia, Haojie Liu, Zhan Ma

The Object-Based Image Coding (OBIC) that was extensively studied about two decades ago, promised a vast application perspective for both ultra-low bitrate communication and high-level semantical content understanding, but it had rarely been used due to the inefficient compact representation of object with arbitrary shape.

Image Compression Semantic Segmentation

Learned Video Compression via Joint Spatial-Temporal Correlation Exploration

no code implementations13 Dec 2019 Haojie Liu, Han Shen, Lichao Huang, Ming Lu, Tong Chen, Zhan Ma

Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency.

Optical Flow Estimation Video Compression

Neural Image Compression via Non-Local Attention Optimization and Improved Context Modeling

1 code implementation11 Oct 2019 Tong Chen, Haojie Liu, Zhan Ma, Qiu Shen, Xun Cao, Yao Wang

This paper proposes a novel Non-Local Attention optmization and Improved Context modeling-based image compression (NLAIC) algorithm, which is built on top of the deep nerual network (DNN)-based variational auto-encoder (VAE) structure.

Image Compression MS-SSIM +1

A Dual Camera System for High Spatiotemporal Resolution Video Acquisition

no code implementations28 Sep 2019 Ming Cheng, Zhan Ma, M. Salman Asif, Yiling Xu, Haojie Liu, Wenbo Bao, Jun Sun

This paper presents a dual camera system for high spatiotemporal resolution (HSTR) video acquisition, where one camera shoots a video with high spatial resolution and low frame rate (HSR-LFR) and another one captures a low spatial resolution and high frame rate (LSR-HFR) video.

Learned Point Cloud Geometry Compression

2 code implementations26 Sep 2019 Jianqiang Wang, Hao Zhu, Zhan Ma, Tong Chen, Haojie Liu, Qiu Shen

This paper presents a novel end-to-end Learned Point Cloud Geometry Compression (a. k. a., Learned-PCGC) framework, to efficiently compress the point cloud geometry (PCG) using deep neural networks (DNN) based variational autoencoders (VAE).

Surface Reconstruction

PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation

no code implementations16 Sep 2019 Haojie Liu, Kang Liao, Chunyu Lin, Yao Zhao, Yulan Guo

In this paper, we propose a novel Pseudo-LiDAR interpolation network (PLIN) to increase the frequency of LiDAR sensors.

Autonomous Driving

Non-local Attention Optimized Deep Image Compression

no code implementations22 Apr 2019 Haojie Liu, Tong Chen, Peiyao Guo, Qiu Shen, Xun Cao, Yao Wang, Zhan Ma

This paper proposes a novel Non-Local Attention Optimized Deep Image Compression (NLAIC) framework, which is built on top of the popular variational auto-encoder (VAE) structure.

Image Compression MS-SSIM +1

Extreme Image Coding via Multiscale Autoencoders With Generative Adversarial Optimization

no code implementations8 Apr 2019 Chao Huang, Haojie Liu, Tong Chen, Qiu Shen, Zhan Ma

We propose a MultiScale AutoEncoder(MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate.

Image Compression

Gated Context Model with Embedded Priors for Deep Image Compression

no code implementations27 Feb 2019 Haojie Liu, Tong Chen, Peiyao Guo, Qiu Shen, Zhan Ma

Besides, a field study on perceptual quality is also given via a dedicated subjective assessment, to compare the efficiency of our proposed methods and other conventional image compression methods.

Image Compression Image Reconstruction +2

Deep Image Compression via End-to-End Learning

1 code implementation5 Jun 2018 Haojie Liu, Tong Chen, Qiu Shen, Tao Yue, Zhan Ma

We present a lossy image compression method based on deep convolutional neural networks (CNNs), which outperforms the existing BPG, WebP, JPEG2000 and JPEG as measured via multi-scale structural similarity (MS-SSIM), at the same bit rate.

Image Compression MS-SSIM +3

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