Alert button
Picture for Siwei Ma

Siwei Ma

Alert button

A Neural-network Enhanced Video Coding Framework beyond ECM

Feb 13, 2024
Yanchen Zhao, Wenxuan He, Chuanmin Jia, Qizhe Wang, Junru Li, Yue Li, Chaoyi Lin, Kai Zhang, Li Zhang, Siwei Ma

Viaarxiv icon

Scalable Face Image Coding via StyleGAN Prior: Towards Compression for Human-Machine Collaborative Vision

Dec 25, 2023
Qi Mao, Chongyu Wang, Meng Wang, Shiqi Wang, Ruijie Chen, Libiao Jin, Siwei Ma

Viaarxiv icon

Spatial-Temporal Transformer based Video Compression Framework

Sep 21, 2023
Yanbo Gao, Wenjia Huang, Shuai Li, Hui Yuan, Mao Ye, Siwei Ma

Figure 1 for Spatial-Temporal Transformer based Video Compression Framework
Figure 2 for Spatial-Temporal Transformer based Video Compression Framework
Figure 3 for Spatial-Temporal Transformer based Video Compression Framework
Figure 4 for Spatial-Temporal Transformer based Video Compression Framework
Viaarxiv icon

MPAI-EEV: Standardization Efforts of Artificial Intelligence based End-to-End Video Coding

Sep 14, 2023
Chuanmin Jia, Feng Ye, Fanke Dong, Kai Lin, Leonardo Chiariglione, Siwei Ma, Huifang Sun, Wen Gao

Figure 1 for MPAI-EEV: Standardization Efforts of Artificial Intelligence based End-to-End Video Coding
Figure 2 for MPAI-EEV: Standardization Efforts of Artificial Intelligence based End-to-End Video Coding
Figure 3 for MPAI-EEV: Standardization Efforts of Artificial Intelligence based End-to-End Video Coding
Figure 4 for MPAI-EEV: Standardization Efforts of Artificial Intelligence based End-to-End Video Coding
Viaarxiv icon

Extreme Image Compression using Fine-tuned VQGAN Models

Aug 07, 2023
Qi Mao, Tinghan Yang, Yinuo Zhang, Shuyin Pan, Meng Wang, Shiqi Wang, Siwei Ma

Figure 1 for Extreme Image Compression using Fine-tuned VQGAN Models
Figure 2 for Extreme Image Compression using Fine-tuned VQGAN Models
Figure 3 for Extreme Image Compression using Fine-tuned VQGAN Models
Figure 4 for Extreme Image Compression using Fine-tuned VQGAN Models
Viaarxiv icon

SpikeCodec: An End-to-end Learned Compression Framework for Spiking Camera

Jun 25, 2023
Kexiang Feng, Chuanmin Jia, Siwei Ma, Wen Gao

Figure 1 for SpikeCodec: An End-to-end Learned Compression Framework for Spiking Camera
Figure 2 for SpikeCodec: An End-to-end Learned Compression Framework for Spiking Camera
Figure 3 for SpikeCodec: An End-to-end Learned Compression Framework for Spiking Camera
Figure 4 for SpikeCodec: An End-to-end Learned Compression Framework for Spiking Camera
Viaarxiv icon

Optimization-Inspired Cross-Attention Transformer for Compressive Sensing

Apr 27, 2023
Jiechong Song, Chong Mou, Shiqi Wang, Siwei Ma, Jian Zhang

Figure 1 for Optimization-Inspired Cross-Attention Transformer for Compressive Sensing
Figure 2 for Optimization-Inspired Cross-Attention Transformer for Compressive Sensing
Figure 3 for Optimization-Inspired Cross-Attention Transformer for Compressive Sensing
Figure 4 for Optimization-Inspired Cross-Attention Transformer for Compressive Sensing
Viaarxiv icon

Machine Perception-Driven Image Compression: A Layered Generative Approach

Apr 14, 2023
Yuefeng Zhang, Chuanmin Jia, Jiannhui Chang, Siwei Ma

Figure 1 for Machine Perception-Driven Image Compression: A Layered Generative Approach
Figure 2 for Machine Perception-Driven Image Compression: A Layered Generative Approach
Figure 3 for Machine Perception-Driven Image Compression: A Layered Generative Approach
Figure 4 for Machine Perception-Driven Image Compression: A Layered Generative Approach
Viaarxiv icon

Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation

Mar 21, 2023
Wenkang Shan, Zhenhua Liu, Xinfeng Zhang, Zhao Wang, Kai Han, Shanshe Wang, Siwei Ma, Wen Gao

Figure 1 for Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
Figure 2 for Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
Figure 3 for Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
Figure 4 for Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
Viaarxiv icon