Biography

Currently, I am a last year Phd student studying Computer Science at Durham University and advised by Prof. Yang Long. My current research lies at the intersection of computer vision, computer graphics, and machine learning, focusing on understanding the dynamic three-dimensional world as captured by everyday images and videos. By moving beyond the limitations of traditional 2D or 2.5D representations, I strive to develop multi-view reconstruction techniques that offer a comprehensive understanding of complex environments. Ultimately, my long-term goal is to create intelligent systems capable of perceiving, interpreting, and continually learning from the ever-evolving physical world.

News

∙ [2025.01] One paper is accepted to TPAMI 2025.
∙ [2024.08] One paper is accepted to PR 2024.
∙ [2023.08] One paper is accepted to TCSVT 2023.

Publications

Laser

Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields

Xingyu Miao, Haoran Duan, Yang Bai, Tejal Shah, Jun Song, Yang Long, Rajiv Ranjan, Ling Shao
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
Paper | Code


CTNeRF

CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Video

Xingyu Miao, Yang Bai, Haoran Duan, Yawen Huang, Fan Wan, Yang Long, Yefeng Zheng
Pattern Recognition (PR), 2024
Paper | Code


DS-Depth

DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume

Xingyu Miao, Yang Bai, Haoran Duan, Yawen Huang, Fan Wan, Xinxing Xu, Yang Long, Yefeng Zheng
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023
Paper | Code