Research

Research Directions

We study intelligent visual information processing and transmission across five research directions centered on efficient compression, intelligent analysis, and immersive presentation.

Overview

Intelligent Visual Information Processing and Transmission

The Intelligent Visual Coding Team focuses on intelligent visual information processing and transmission. Our work spans five major directions: image/video coding and communication, visual perception and image quality assessment, 3D video processing, virtual/augmented reality, and artificial intelligence with visual applications.

Efficient Compression Intelligent Analysis Immersive Presentation Visual Communication AI Applications

Direction 01

Image/Video Coding and Communication

We investigate next-generation intelligent coding frameworks for efficient compression, transmission, and reconstruction of images and videos. Topics include deep learning-based end-to-end image/video coding, semantic communication for visual information, adaptive rate control, and bit allocation to improve quality and efficiency over limited-bandwidth and complex channels.

End-to-End Image/Video Coding Semantic Communication Rate Control Bit Allocation

Video coding optimization framework — Video Coding Optimization Framework

Conventional and end-to-end video compression frameworks — Conventional and End-to-End Video Compression

Direction 02

Visual Perception and Image Quality Assessment

By combining human visual system characteristics with machine learning, we study perceptual modeling and both objective and subjective quality assessment for images, videos, and point clouds. We develop no-reference and reduced-reference models and explore visual attention and semantic-aware assessment for coding optimization, transmission scheduling, and enhanced user experience.

Visual Perception Modeling Image/Video/Point Cloud Quality No-/Reduced-Reference Models User Experience

Subjective and objective point cloud quality assessment workflow — Point Cloud Quality Assessment Workflow

Human visual perception — Human Visual Perception

Direction 03

3D Video Processing

For 3D visual data such as point clouds, light fields, and multiview video, we study acquisition, representation, compression, reconstruction, and rendering. We develop efficient 3D geometry and texture coding methods for six-degrees-of-freedom (6DoF) immersive experiences and explore applications in virtual environments and remote interaction.

Point Clouds Light Fields Multiview Video 6DoF

3D video coding framework — 3D Video Coding Framework

3D video live streaming system — 3D Video Live Streaming System

Direction 04

Virtual Reality / Augmented Reality

We study real-time 3D reconstruction, mixed-reality rendering, visual localization and tracking, and multimodal interaction for generating, fusing, and presenting visual information in VR/AR. Our goal is to overcome bottlenecks in high-frame-rate, low-latency, high-fidelity graphics and displays for immersive visual systems.

Real-Time 3D Reconstruction Mixed-Reality Rendering Visual Localization & Tracking Multimodal Interaction

VR and AR applications — VR/AR Applications

VR video live streaming system — VR Video Live Streaming System

Direction 05

Artificial Intelligence and Visual Applications

We explore frontier AI applications in visual information processing, including deep learning-based image enhancement and restoration, video understanding and generation, cross-modal vision-language modeling, visual perception for autonomous driving, and medical image analysis.

Image Enhancement & Restoration Video Understanding & Generation Vision-Language Modeling Intelligent Visual Systems

Frontier applications of artificial intelligence — Frontier AI Applications

Intelligent video analysis — Intelligent Video Analysis

Open Positions

We continuously recruit Ph.D. students, master's students, and postdoctoral researchers. Outstanding undergraduates interested in our research are also welcome to join the lab.

Ph.D. Students Master's Students Postdoctoral Researchers Undergraduate Research

Contact

We welcome academic and industry collaboration in intelligent visual coding, visual quality assessment, 3D media, VR/AR, and AI-powered visual applications.

zhangyun2@mail.sysu.edu.cn