Research Projects

1. Multimedia Coding and Processing

The research work includes 3D point cloud coding, image/video coding, multimodal coding, quality enhancement, and the related standardization efforts. We mainly focus on advanced deep learning solutions for coding optimization, and devise various methods to obtain better rate-distortion performance with flexibility and scalability. We have recently published high quality papers on IEEE TIP, IEEE TCSVT, IEEE TMM, IEEE TGRS, ACM MM, CVPR, AAAI, DCC, etc., and participated into the standardization work of MPEG and AVS. The monograph titled “Point Cloud Compression: Technologies and Standardization” has been published by Springer Nature in 2024, and another monograph titled “AI-based Image and Video Coding: Methods, Standards, and Applications” will appear soon.

AdaDPCC: Adaptive Rate Control and Rate-Distortion-Complexity Optimization for Dynamic Point Cloud Compression
AAAI, 2025.
UniPCGC: Towards Practical Point Cloud Geometry Compression via An Efficient Unified Approach
AAAI, 2025.
Saliency Segmentation Oriented Deep Image Compression with Novel Bit Allocation
IEEE TIP, 2025.
3D Point Cloud Attribute Compression Using Diffusion-based Texture-aware Intra Prediction
IEEE TCSVT, 2024.
Enlarged Motion-Aware and Frequency-Aware Network for Compressed Video Artifact Reduction
IEEE TCSVT, 2024.
Fast Inter-Frame Motion Prediction for Compressed Dynamic Point Cloud Attribute Enhancement
AAAI, 2024.
End-to-End RGB-D Image Compression via Exploiting Channel-Modality Redundancy
AAAI, 2024.
ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision
ACM MM, 2024.
ViewPCGC: View-Guided Learned Point Cloud Geometry Compression
ACM MM, 2024.
SPCGC: Scalable Point Cloud Geometry Compression for Machine Vision
ICRA, 2024.
Learned Rate Control for Frame-Level Adaptive Neural Video Compression via Dynamic Neural Network
ECCV, 2024.
SUR-Driven Video Coding Rate Control for Jointly Optimizing Perceptual Quality and Buffer Control
IEEE TIP, 2023.
Block-Adaptive Point Cloud Attribute Coding with Region-Aware Optimized Transform
IEEE TCSVT, 2023.
Semantic Point Cloud Upsampling
IEEE TMM, 2023.
OctAttention: Octree-based Large-scale Contexts Model for Point Cloud Compression
AAAI, 2022.

2. Human and Machine Perception Modeling

The research work includes datasets and subjective experiment platforms, human perception models (quality assessment and saliency detection), and machine perception models (segmentation, detection, and understanding). We have recently published high quality papers on IEEE TPAMI, IEEE TCSVT, IEEE TMM, IEEE TNNLS, ACM MM, CVPR, ECCV, AAAI, ICRA, DCC, etc. The monograph titled “Deep Learning for 3D Point Clouds” has been published by Springer Nature in 2025.

Stochasticity-aware No-Reference Point Cloud Quality Assessment
IJCAI, 2025.
Point Cloud Semantic Segmentation With Sparse and Inhomogeneous Annotations
AAAI, 2025.
VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment
AAAI, 2025.
Less is More: Label Recommendation for Weakly Supervised Point Cloud Semantic Segmentation
AAAI, 2024.
Point-MPP: Point Cloud Self-supervised Learning from Masked Position Prediction
IEEE TNNLS, 2024.
Zoom to Perceive Better: No-reference Point Cloud Quality Assessment via Exploring Effective Multiscale Feature
IEEE TCSVT, 2024.
Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering
CVPR, 2023.
A Thorough Benchmark and A New Model for Light Field Saliency Detection
IEEE TPAMI, 2023.
Unified Information Fusion Network for Multi-Modal RGB-D and RGB-T Salient Object Detection
IEEE TCSVT, 2022.
Salient Object Detection for Point Clouds
ECCV, 2022.

3. Software and Hardware Implementations

The research work includes light-weight algorithms and models, hardware acceleration and implementations, and open source projects. We have recently published high quality papers on IEEE TIP, IJCV, IEEE TNNLS, ACM MM, ICCV, etc. We established several open source projects for multimedia computing and AI, including OpenAICoding, OpenPointCloud, OpenDatasets, etc.

Low Complexity Coding Unit Decision in Video-Based Point Cloud Compression
IEEE TIP, 2024.
Efficient Neural Network Compression Inspired by Compressive Sensing
IEEE TNNLS, 2024.
OpenHardwareVC: An Open Source Library for 8K UHD Video Coding Hardware Implementation
ACM MM, 2024.
OpenDIC: An Open-Source Library and Performance Evaluation for Deep-learning-based Image Compression
ACM MM, 2024.
OpenDMC: An Open-Source Library and Performance Evaluation for Deep-learning-based Multi-frame Compression
ACM MM, 2024.
OpenPointCloud: An Open-Source Algorithm Library of Deep Learning Based Point Cloud Compression
ACM MM, 2024.
Interpretable Task-inspired Adaptive Filter Pruning For Neural Networks Under Multiple Constraints
IJCV, 2024.
AdaNIC: Towards Practical Neural Image and Compression via Dynamic Transform Routing
ICCV, 2024.
Rate-Distortion-Guided Learning Approach with Cross-Projection Information for V-PCC Fast CU Decision
ACM MM, 2023.
OpenFastVC: An Open Source Library for Video Coding Fast Algorithm Implementation
ACM MM, 2023.

4. Immersive Media and Autonomous Driving Applications

Building upon the above research projects, we are further investigating the related technologies to promote the practical applications of immersive media and autonomous driving, including multimodal data compression, quality assessment and enhancement, real-time implementations, generative AI and world model, multimodal large model-based perception and decision, etc. We also have close collaborations with several renowned high-tech companies. The aim of this research project is propelling the next generation innovations of immersive media and autonomous driving to benefit the human society.