Media is the heartbeat of our digital age, shaping the way we connect, learn, and experience the world.

Leveraging cutting-edge deep learning and the vast prowess of Large Language Models, we’re at the forefront of innovation in video processing, video compression, video generation, 3D reconstruction, and multimodal media interactive.

Join our lab to revolutionize media tech, crafting a more connected, immersive, and interactive world.

@sjtu-medialab   @media_tech

Follow our Github for academic open source projects.
Follow our Wechat Official Account for the latest media technology progress.

Recent Publications

A Priority Aware Free Viewpoint Video Transmit Scheme Based on QUIC
Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views
Hdrtvformer: Efficient Sdrtv-to-Hdrtv via Affine Transformation and Spatial-Aware Transformer
Neural Rate Control for Learned Video Compression
No-Reference Quality Assessment of Text-to-Image Generation