I am currently a graduate student in School of Computer and Information Technology at Beijing Jiaotong University, luckily advised by Prof. Yi Liu. I received B.S. in Computer Science from Beijing Jiaotong University in 2020. I am also a research intern at Cognitive Computing Lab, Baidu Research, luckily advised by Dr. Zeke Xie.
I am interested in 3D vision and autonomous driving , and my current research focuses on leveraging neural fields to enhance the quality and the robustness in autonomous driving simulations.
I am actively looking for a PhD position for Fall 2024! Check out my CV here.
π Educations
- 2020.06 - 2024.06(expected), Master of Computer Science, School of Computer and Information Technology, Beijing Jiaotong University, Beijing.
- 2016.09 - 2020.06, Bachelor of Computer Science, School of Computer and Information Technology, Beijing Jiaotong University, Beijing.
π» Internships
- 2022.05 - 2024.01(now), Research Intern, Cognitive Computing Lab, Baidu Research.
- 2020.10 - 2022.01, Visiting Student, Han lab, PKU.
π₯ News
- 2024.01: Β π One paper Neural Field Classifier is accepted by ICLR 2024.
- 2023.08: Β π SDFStdudio has supported S3IM.
- 2023.08: Β π₯ We release S3IM(βοΈ200+).
- 2023.07: Β π One paper S3IM is accepted by ICCV 2023.
π Publications and Manuscripts
Neural Field Classifiers via Target Encoding and Classification Loss.
Xindi Yang, Zeke Xie, Xiong Zhou, Boyu Liu, Buhua Liu, Yi Liu, Haoran Wang, Yunfeng Cai, Mingming Sun.
- Neural Field Classifiers via Target Encoding and Classification Loss can significantly outperform the standard regression-based neural field counterparts.
S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fields.
Zeke Xie*, Xindi Yang*, Yujie Yang, Qi Sun, Yixiang Jiang, Haoran Wang, Yunfeng Cai, Mingming Sun (*equal contribution).
- S3IM is a plug-and-play loss, effective and robust in various difficult tasks.
- Academic Impact: Our work are promoted by more than 4 media and forums, such as η₯δΉ, ζδΈεΉ³ε°
Coordinate-Wise Monotonic Transformations for Privacy Preserving Facial Age Estimation.
Xinyu Yang, Runhan Li, Xindi Yang, Yong Zhou, Yi Liu, Jing-Dong J. Han.
- We present an approach for facial data masking that preserves age-related features using coordinate-wise monotonic transformations.
π Honors and Awards
- 2023, Outstanding Intern of the Year, Baidu Research
- 2016-2022, Model Student of Academic Records of Beijing Jiaotong University
- 2018, National Contemporary Undergraduate Mathematical Contest IN Modeling in China, First Prize in Beijing region