About PKU MMCAL Team

We are the Multimedia Computing and AI Lab (MMCAL), from the School of Electronic and Computer Engineering, Peking University, Shenzhen, China.

We are working on Multimedia Computing and Artificial Intelligence, especially Multimedia Coding and Processing, 3D Vision and Multimodal Learning, Efficient Computing Systems and Applications.

Intelligent 3D Visual Data Coding and Processing

• 3D Visual Data Coding (3D Point Cloud Coding, 3D Gaussian Splatting Compression/Rendering, 2D/3D Image/Video Coding, Deep Learning-Based Coding, Human and Machine Perception-Driven Coding)
• 3D Visual Data Quality Assessment and Enhancement
• AI-based Coding Standards and Transmission Systems

Spatial Intelligence and Embodied Intelligence

• World Models
• Vision-Language-Action (VLA) Models
• 3D Multimodal Reconstruction/Generation/Perception/Understanding

Efficient Computing Systems and Applications

• Model Compression and Acceleration for Inference and Deployment Optimization
• Heterogeneous Computing Platform with CPU/GPU/FPGA/ASIC/MCU
• Embedded Hardware and Software Systems for Emerging Applications

We aim to conduct in-depth research on the theories and methods of 3D vision and multimodal information processing, and promote the applications of related technologies in immersive interactive media communication (VR/AR/MR) and autonomous intelligent unmanned systems (autonomous driving/robotics).