Jun Xu

Jun Xu received his B.E. degree from Shanghai Jiao Tong University, Shanghai, China, in 2020. He is currently pursuing a Ph.D. degree with the Department of Electronic Engineering at Shanghai Jiao Tong University, Shanghai, China. His research interests are diverse and primarily focused on audio/video encoding and multimedia systems.

In the realm of video encoding, Jun Xu has made contributions to encoding acceleration techniques, optimizing the encoding process to achieve faster and more efficient video compression without compromising quality. Specifically, his work on accelerating VVC intra-frame coding was published in ICIP2022.

On the audio encoding front, Jun Xu is particularly interested in end-to-end neural compression. This cutting-edge approach leverages deep learning techniques to compress audio data more effectively than traditional methods. By utilizing neural networks, his research aims to reduce the bandwidth required for audio transmission while maintaining high fidelity, which is essential for applications such as streaming services and real-time communications.

Jun Xu has also been heavily involved in the development of advanced multimedia systems. He has worked on some projects ranging from real-time 2D face video calls to sophisticated talking face video calls that can drive photorealistic avatars. His work extends to virtual avatar video calls and even 3D video calls, pushing the boundaries of how people can interact visually over long distances. Specifically, his work on multiple forms of virtual videoconferencing has published in IBC2022.

Additionally, Jun Xu has explored the field of 3D streaming media, particularly focusing on free-viewpoint live streaming systems that utilize video frame interpolation. This innovative research enables viewers to watch live events from any desired angle, enhancing the immersive experience of live broadcasts.