Search Results for author: Shan Liu

Found 61 papers, 16 papers with code

Corner-to-Center Long-range Context Model for Efficient Learned Image Compression

no code implementations29 Nov 2023 Yang Sui, Ding Ding, Xiang Pan, Xiaozhong Xu, Shan Liu, Bo Yuan, Zhenzhong Chen

To tackle this issue, we conduct an in-depth analysis of the performance degradation observed in existing parallel context models, focusing on two aspects: the Quantity and Quality of information utilized for context prediction and decoding.

Image Compression

SJTU-TMQA: A quality assessment database for static mesh with texture map

no code implementations27 Sep 2023 Bingyang Cui, Qi Yang, Kaifa Yang, Yiling Xu, Xiaozhong Xu, Shan Liu

However, little research has been done on the quality assessment of textured meshes, which hinders the development of quality-oriented applications, such as mesh compression and enhancement.

Dynamic Kernel-Based Adaptive Spatial Aggregation for Learned Image Compression

no code implementations17 Aug 2023 Huairui Wang, Nianxiang Fu, Zhenzhong Chen, Shan Liu

In this paper, we focus on extending spatial aggregation capability and propose a dynamic kernel-based transform coding.

Image Compression valid

GeodesicPSIM: Predicting the Quality of Static Mesh with Texture Map via Geodesic Patch Similarity

no code implementations9 Aug 2023 Qi Yang, Joel Jung, Xiaozhong Xu, Shan Liu

A two-step patch cropping algorithm and a patch texture mapping module refine the size of 1-hop geodesic patches and build the relationship between the mesh geometry and color information, resulting in the generation of 1-hop textured geodesic patches.

TDMD: A Database for Dynamic Color Mesh Subjective and Objective Quality Explorations

no code implementations3 Aug 2023 Qi Yang, Joel Jung, Timon Deschamps, Xiaozhong Xu, Shan Liu

Dynamic colored meshes (DCM) are widely used in various applications; however, these meshes may undergo different processes, such as compression or transmission, which can distort them and degrade their quality.

TSMD: A Database for Static Color Mesh Quality Assessment Study

no code implementations3 Aug 2023 Qi Yang, Joel Jung, Haiqiang Wang, Xiaozhong Xu, Shan Liu

Static meshes with texture map are widely used in modern industrial and manufacturing sectors, attracting considerable attention in the mesh compression community due to its huge amount of data.

Layer-wise Representation Fusion for Compositional Generalization

no code implementations20 Jul 2023 Yafang Zheng, Lei Lin, Zhaohong Lai, Binling Wang, Shan Liu, Biao Fu, Wenhao Rao, PeiGen Ye, Yidong Chen, Xiaodong Shi

However, most previous studies mainly concentrate on enhancing token-level semantic information to alleviate the representations entanglement problem, rather than composing and using the syntactic and semantic representations of sequences appropriately as humans do.

Once-Training-All-Fine: No-Reference Point Cloud Quality Assessment via Domain-relevance Degradation Description

no code implementations4 Jul 2023 Yipeng Liu, Qi Yang, Yujie Zhang, Yiling Xu, Le Yang, Xiaozhong Xu, Shan Liu

Second, to reduce the significant domain discrepancy, we establish an intermediate domain, the description domain, based on insights from subjective experiments, by considering the domain relevance among samples located in the perception domain and learning a structured latent space.

Point Cloud Quality Assessment regression

Reconstruction Distortion of Learned Image Compression with Imperceptible Perturbations

no code implementations1 Jun 2023 Yang Sui, Zhuohang Li, Ding Ding, Xiang Pan, Xiaozhong Xu, Shan Liu, Zhenzhong Chen

Learned Image Compression (LIC) has recently become the trending technique for image transmission due to its notable performance.

Image Compression Image Reconstruction

Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization

no code implementations20 May 2023 Lei Lin, Shuangtao Li, Yafang Zheng, Biao Fu, Shan Liu, Yidong Chen, Xiaodong Shi

There is mounting evidence that one of the reasons hindering CG is the representation of the encoder uppermost layer is entangled, i. e., the syntactic and semantic representations of sequences are entangled.

PanelNet: Understanding 360 Indoor Environment via Panel Representation

no code implementations CVPR 2023 Haozheng Yu, Lu He, Bing Jian, Weiwei Feng, Shan Liu

To reduce the negative impact of panoramic distortion, we incorporate a panel geometry embedding network that encodes both the local and global geometric features of a panel.

Depth Estimation Semantic Segmentation

A Tiny Machine Learning Model for Point Cloud Object Classification

no code implementations20 Mar 2023 Min Zhang, Jintang Xue, Pranav Kadam, Hardik Prajapati, Shan Liu, C. -C. Jay Kuo

On the other hand, the model size and inference complexity of DGCNN are 42X and 1203X of those of Green-PointHop, respectively.

S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classification

no code implementations22 Feb 2023 Pranav Kadam, Hardik Prajapati, Min Zhang, Jintang Xue, Shan Liu, C. -C. Jay Kuo

Many point cloud classification methods are developed under the assumption that all point clouds in the dataset are well aligned with the canonical axes so that the 3D Cartesian point coordinates can be employed to learn features.

3D Point Cloud Classification Classification +1

gpcgc: a green point cloud geometry coding method

no code implementations13 Feb 2023 Qingyang Zhou, Shan Liu, C. -C. Jay Kuo

A low-complexity point cloud compression method called the Green Point Cloud Geometry Codec (GPCGC), is proposed to encode the 3D spatial coordinates of static point clouds efficiently.


Efficient Hierarchical Entropy Model for Learned Point Cloud Compression

no code implementations CVPR 2023 Rui Song, Chunyang Fu, Shan Liu, Ge Li

Learning an accurate entropy model is a fundamental way to remove the redundancy in point cloud compression.

Changes from Classical Statistics to Modern Statistics and Data Science

no code implementations30 Oct 2022 Kai Zhang, Shan Liu, Momiao Xiong

We urgently need to shift the paradigm for data analysis from the classical Euclidean data analysis to both Euclidean and non Euclidean data analysis and develop more and more innovative methods for describing, estimating and inferring non Euclidean geometries of modern real datasets.

GPA-Net:No-Reference Point Cloud Quality Assessment with Multi-task Graph Convolutional Network

no code implementations29 Oct 2022 Ziyu Shan, Qi Yang, Rui Ye, Yujie Zhang, Yiling Xu, Xiaozhong Xu, Shan Liu

To extract effective features for PCQA, we propose a new graph convolution kernel, i. e., GPAConv, which attentively captures the perturbation of structure and texture.

Philosophy Point Cloud Quality Assessment

Robust Human Matting via Semantic Guidance

1 code implementation11 Oct 2022 Xiangguang Chen, Ye Zhu, Yu Li, Bingtao Fu, Lei Sun, Ying Shan, Shan Liu

Unlike previous works, our framework is data efficient, which requires a small amount of matting ground-truth to learn to estimate high quality object mattes.

Image Matting Segmentation

Point Cloud Quality Assessment using 3D Saliency Maps

no code implementations30 Sep 2022 Zhengyu Wang, Yujie Zhang, Qi Yang, Yiling Xu, Jun Sun, Shan Liu

Considering the importance of saliency detection in quality assessment, we propose an effective full-reference PCQA metric which makes the first attempt to utilize the saliency information to facilitate quality prediction, called point cloud quality assessment using 3D saliency maps (PQSM).

Point Cloud Quality Assessment Saliency Detection

Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-Resolution

no code implementations18 Jul 2022 Han Zhu, Zhenzhong Chen, Shan Liu

In addition, the KRNets are optimized in a meta-learning manner to ensure the knowledge transferring and the student learning are beneficial to improving the reconstructed quality of the student.

Image Super-Resolution Knowledge Distillation +1

Enhancing HDR Video Compression through CNN-based Effective Bit Depth Adaptation

1 code implementation18 Jul 2022 Chen Feng, Zihao Qi, Duolikun Danier, Fan Zhang, Xiaozhong Xu, Shan Liu, David Bull

In this work, we modify the MFRNet network architecture to enable multiple frame processing, and the new network, multi-frame MFRNet, has been integrated into the EBDA framework using two Versatile Video Coding (VVC) host codecs: VTM 16. 2 and the Fraunhofer Versatile Video Encoder (VVenC 1. 4. 0).

Video Compression

FAIVConf: Face enhancement for AI-based Video Conference with Low Bit-rate

no code implementations8 Jul 2022 Zhengang Li, Sheng Lin, Shan Liu, Songnan Li, Xue Lin, Wei Wang, Wei Jiang

Recently, high-quality video conferencing with fewer transmission bits has become a very hot and challenging problem.

Face Generation Face Swapping +1

Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction

no code implementations CVPR 2022 Zhihao Hu, Guo Lu, Jinyang Guo, Shan Liu, Wei Jiang, Dong Xu

The previous deep video compression approaches only use the single scale motion compensation strategy and rarely adopt the mode prediction technique from the traditional standards like H. 264/H. 265 for both motion and residual compression.

Motion Compensation Motion Estimation +1

Neural Texture Extraction and Distribution for Controllable Person Image Synthesis

1 code implementation CVPR 2022 Yurui Ren, Xiaoqing Fan, Ge Li, Shan Liu, Thomas H. Li

Our model is trained to predict human images in arbitrary poses, which encourages it to extract disentangled and expressive neural textures representing the appearance of different semantic entities.

Image Generation

PCRP: Unsupervised Point Cloud Object Retrieval and Pose Estimation

no code implementations16 Feb 2022 Pranav Kadam, Qingyang Zhou, Shan Liu, C. -C. Jay Kuo

An unsupervised point cloud object retrieval and pose estimation method, called PCRP, is proposed in this work.

Point Cloud Registration Pose Estimation +1

OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression

1 code implementation12 Feb 2022 Chunyang Fu, Ge Li, Rui Song, Wei Gao, Shan Liu

In point cloud compression, sufficient contexts are significant for modeling the point cloud distribution.

LSVC: A Learning-Based Stereo Video Compression Framework

no code implementations CVPR 2022 Zhenghao Chen, Guo Lu, Zhihao Hu, Shan Liu, Wei Jiang, Dong Xu

In this work, we propose the first end-to-end optimized framework for compressing automotive stereo videos (i. e., stereo videos from autonomous driving applications) from both left and right views.

Autonomous Driving Motion Compensation +1

GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Method

no code implementations8 Dec 2021 Pranav Kadam, Min Zhang, Jiahao Gu, Shan Liu, C. -C. Jay Kuo

GreenPCO is an unsupervised learning method that predicts object motion by matching features of consecutive point cloud scans.

Benchmarking Visual Odometry

Online Meta Adaptation for Variable-Rate Learned Image Compression

no code implementations16 Nov 2021 Wei Jiang, Wei Wang, Songnan Li, Shan Liu

This work addresses two major issues of end-to-end learned image compression (LIC) based on deep neural networks: variable-rate learning where separate networks are required to generate compressed images with varying qualities, and the train-test mismatch between differentiable approximate quantization and true hard quantization.

Image Compression Meta-Learning +1

GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds

no code implementations24 Sep 2021 Min Zhang, Pranav Kadam, Shan Liu, C. -C. Jay Kuo

It is named GSIP (Green Segmentation of Indoor Point clouds) and its performance is evaluated on a representative large-scale benchmark -- the Stanford 3D Indoor Segmentation (S3DIS) dataset.

Segmentation Semantic Segmentation

PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering

1 code implementation ICCV 2021 Yurui Ren, Ge Li, Yuanqi Chen, Thomas H. Li, Shan Liu

The proposed model can generate photo-realistic portrait images with accurate movements according to intuitive modifications.

Image Generation Neural Rendering

Combining Attention with Flow for Person Image Synthesis

no code implementations4 Aug 2021 Yurui Ren, Yubo Wu, Thomas H. Li, Shan Liu, Ge Li

Pose-guided person image synthesis aims to synthesize person images by transforming reference images into target poses.

Image Generation

Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression

no code implementations15 Jun 2021 Sheng Lin, Wei Jiang, Wei Wang, Kaidi Xu, Yanzhi Wang, Shan Liu, Songnan Li

Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices.

Neural Network Compression

Recent Standard Development Activities on Video Coding for Machines

no code implementations26 May 2021 Wen Gao, Shan Liu, Xiaozhong Xu, Manouchehr Rafie, Yuan Zhang, Igor Curcio

Specifically, we will first provide an overview of the MPEG VCM group including use cases, requirements, processing pipelines, plan for potential VCM standards, followed by the evaluation framework including machine-vision tasks, dataset, evaluation metrics, and anchor generation.

object-detection Object Detection

Substitutional Neural Image Compression

no code implementations16 May 2021 Xiao Wang, Wei Jiang, Wei Wang, Shan Liu, Brian Kulis, Peter Chin

The key idea is to replace the image to be compressed with a substitutional one that outperforms the original one in a desired way.

Image Compression

Tencent Video Dataset (TVD): A Video Dataset for Learning-based Visual Data Compression and Analysis

no code implementations12 May 2021 Xiaozhong Xu, Shan Liu, Zeqiang Li

Learning-based visual data compression and analysis have attracted great interest from both academia and industry recently.

Data Compression object-detection +1

R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Method

1 code implementation15 Mar 2021 Pranav Kadam, Min Zhang, Shan Liu, C. -C. Jay Kuo

Inspired by the recent PointHop classification method, an unsupervised 3D point cloud registration method, called R-PointHop, is proposed in this work.

Dimensionality Reduction Point Cloud Registration +1

An Optimized H.266/VVC Software Decoder On Mobile Platform

no code implementations5 Mar 2021 Yiming Li, Shan Liu, Yu Chen, Yushan Zheng, Sijia Chen, Bin Zhu, Jian Lou

As the successor of H. 265/HEVC, the new versatile video coding standard (H. 266/VVC) can provide up to 50% bitrate saving with the same subjective quality, at the cost of increased decoding complexity.

High Quality Disparity Remapping With Two-Stage Warping

no code implementations ICCV 2021 Bing Li, Chia-Wen Lin, Cheng Zheng, Shan Liu, Junsong Yuan, Bernard Ghanem, C.-C. Jay Kuo

In the second stage, we derive another warping model to refine warping results in less important regions by eliminating serious distortions in shape, disparity and 3D structure.

Vocal Bursts Intensity Prediction Vocal Bursts Valence Prediction

SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains

1 code implementation10 Dec 2020 Yuanqi Chen, Ge Li, Cece Jin, Shan Liu, Thomas Li

This issue makes the generator lack the incentive from the discriminator to learn high-frequency content of data, resulting in a significant spectrum discrepancy between generated images and real images.

TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis

1 code implementation24 Nov 2020 Qiao Tian, Yi Chen, Zewang Zhang, Heng Lu, LingHui Chen, Lei Xie, Shan Liu

On one hand, we propose to discriminate ground-truth waveform from synthetic one in frequency domain for offering more consistency guarantees instead of only in time domain.

Speech Synthesis

Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation

no code implementations2 Sep 2020 Min Zhang, Pranav Kadam, Shan Liu, C. -C. Jay Kuo

The UFF method exploits statistical correlations of points in a point cloud set to learn shape and point features in a one-pass feedforward manner through a cascaded encoder-decoder architecture.

Classification General Classification +2

Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)

no code implementations2 Sep 2020 Pranav Kadam, Min Zhang, Shan Liu, C. -C. Jay Kuo

An unsupervised point cloud registration method, called salient points analysis (SPA), is proposed in this work.

Point Cloud Registration

Learning Model-Blind Temporal Denoisers without Ground Truths

no code implementations7 Jul 2020 Yanghao Li, Bichuan Guo, Jiangtao Wen, Zhen Xia, Shan Liu, Yuxing Han

Denoisers trained with synthetic data often fail to cope with the diversity of unknown noises, giving way to methods that can adapt to existing noise without knowing its ground truth.

Denoising Management +2

AdaDurIAN: Few-shot Adaptation for Neural Text-to-Speech with DurIAN

no code implementations12 May 2020 Zewang Zhang, Qiao Tian, Heng Lu, Ling-Hui Chen, Shan Liu

This paper investigates how to leverage a DurIAN-based average model to enable a new speaker to have both accurate pronunciation and fluent cross-lingual speaking with very limited monolingual data.

Few-Shot Learning

PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification

2 code implementations9 Feb 2020 Min Zhang, Yifan Wang, Pranav Kadam, Shan Liu, C. -C. Jay Kuo

The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction.

3D Classification 3D Point Cloud Classification +2

C3DVQA: Full-Reference Video Quality Assessment with 3D Convolutional Neural Network

no code implementations30 Oct 2019 Munan Xu, Junming Chen, Haiqiang Wang, Shan Liu, Ge Li, Zhiqiang Bai

However, video quality exhibits different characteristics from static image quality due to the existence of temporal masking effects.

Video Quality Assessment Visual Question Answering (VQA)

Multi-mapping Image-to-Image Translation via Learning Disentanglement

1 code implementation NeurIPS 2019 Xiaoming Yu, Yuanqi Chen, Thomas Li, Shan Liu, Ge Li

Recent advances of image-to-image translation focus on learning the one-to-many mapping from two aspects: multi-modal translation and multi-domain translation.

Disentanglement Image-to-Image Translation +1

PointHop: An Explainable Machine Learning Method for Point Cloud Classification

3 code implementations30 Jul 2019 Min Zhang, Haoxuan You, Pranav Kadam, Shan Liu, C. -C. Jay Kuo

In the attribute building stage, we address the problem of unordered point cloud data using a space partitioning procedure and developing a robust descriptor that characterizes the relationship between a point and its one-hop neighbor in a PointHop unit.

BIG-bench Machine Learning Classification +2

Residual-Guided In-Loop Filter Using Convolution Neural Network

no code implementations29 Jul 2019 Wei Jia, Li Li, Zhu Li, Xiang Zhang, Shan Liu

The block-based coding structure in the hybrid video coding framework inevitably introduces compression artifacts such as blocking, ringing, etc.


Deep AutoEncoder-based Lossy Geometry Compression for Point Clouds

no code implementations18 Apr 2019 Wei Yan, Yiting shao, Shan Liu, Thomas H. Li, Zhu Li, Ge Li

Point cloud is a fundamental 3D representation which is widely used in real world applications such as autonomous driving.

Autonomous Driving Image Compression +1

Generative Adversarial Network based Speaker Adaptation for High Fidelity WaveNet Vocoder

no code implementations6 Dec 2018 Qiao Tian, Bing Yang, Jing Chen, Benlai Tang, Shan Liu

Firstly, due to the noisy input signal of the model, there is still a gap between the quality of generated and natural waveforms.

Vocal Bursts Intensity Prediction

BLP -- Boundary Likelihood Pinpointing Networks for Accurate Temporal Action Localization

no code implementations6 Nov 2018 Weijie Kong, Nannan Li, Shan Liu, Thomas Li, Ge Li

Despite tremendous progress achieved in temporal action detection, state-of-the-art methods still suffer from the sharp performance deterioration when localizing the starting and ending temporal action boundaries.

Action Detection regression +1

Multi-Mapping Image-to-Image Translation with Central Biasing Normalization

no code implementations26 Jun 2018 Xiaoming Yu, Zhenqiang Ying, Thomas Li, Shan Liu, Ge Li

Recent advances in image-to-image translation have seen a rise in approaches generating diverse images through a single network.

Image-to-Image Translation Translation

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