معرفی
Dr. Dan Xu is a Postdoctoral Researcher at the Visual Geometry Group (VGG) within the Department of Engineering Science at the University of Oxford. His research focuses on computer vision, machine learning, and deep learning, particularly for 2D/3D scene understanding tasks including depth estimation, object detection, and image generation.
- Ph.D. in Computer Science (2018), University of Trento
- Research Assistant, Chinese University of Hong Kong
Dr. Xu's research spans computer vision and deep learning, with specific interests in scene depth prediction, visual SLAM, object contour detection, and generative adversarial networks. Recent work explores 3D Gaussian splatting, diffusion models, and multi-task learning.
Key research trends include 3D scene reconstruction, controllable video generation, and multi-modal alignment. His publications emphasize neural radiance fields, attention mechanisms, and generative models for advanced visual tasks.
- Best Paper Award Nominee at ACM Multimedia 2018
- Best Scientific Paper Award at ICPR 2016
- Student Travel Grant (SIGMM/ACM Multimedia 2016)
Dr. Xu contributes to open-source projects and provides training/testing code for his research. He actively reviews for premier journals and conferences including CVPR, NeurIPS, and TPAMI.
