Xiang Ji (纪祥)

I am a postdoc researcher in Next Generation Artificial Intelligence Research Center at Graduate School of Information Science and Technology (IST), The University of Tokyo , supervised by Professor Yinqiang Zheng.

My research interests include computational imaging and generative AI.

Email: ji-xiang [at] ynl.t.u-tokyo.ac.jp

Email  /  LinkedIn  /  Github





profile photo
Selected Publications      (* denotes equal contribution)


HaRP: High Dynamic Range Photosequencing
Xiang Ji*, xxx, Yinqiang Zheng
Ongoing 2025
project page (coming soon) / paper (coming soon) / code (coming soon)

We present a new task of HDR photosequencing

RS-NeRF: Neural Radiance Fields from Rolling Shutter Images
Muyao Niu, Tong Chen, Yifan Zhan, Zhuoxiao Li, Xiang Ji, Yinqiang Zheng
ECCV 2024
paper / code

we present RS NeRF, a method designed to synthesize normal images from novel views using input with RS distortions.


Motion Blur Decomposition with Cross-shutter Guidance
Xiang Ji, Haiyang Jiang, Yinqiang Zheng
CVPR 2024
project page / paper / code / data

We proposed a novel cross-shutter setting for motion decomposition of a single blurry image, inspired by the complementary exposure characteristics of GS and RS cameras.


Rethinking Video Frame Interpolation from Shutter Mode Induced Degradation
Xiang Ji, Zhixiang Wang, Zhihang Zhong, Yinqiang Zheng
ICCV 2023  
paper / code / data / video

We highlighted the effects of shutter mode induced degradations on the VFI task and proposed a generic model to interpolate middle clear frames at arbitrary times

Single Image Deblurring with Row-dependent Blur Magnitude
Xiang Ji, Zhixiang Wang, Shin'ichi Satoh, Yinqiang Zheng
ICCV 2023
paper / code / data

In this paper, we explore a novel in-between exposure mode, called global reset release (GRR) shutter, and propose a residual spatially-compensated and spectrally-enhanced Transformer (RSS-T) block for row-dependent deblurring of a single GRR image.

Blur Interpolation Transformer for Real-World Motion from Blur
Zhihang Zhong, Mingdeng Cao, Xiang Ji, Yinqiang Zheng, Imari Sato
CVPR 2023
project page / paper / code

We propose a blur interpolation transformer (BiT) to effectively unravel the underlying temporal correlation encoded in blur.

Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera with Global
Zhixiang Wang, Xiang Ji, Jia-Bin Huang, Shin'ichi Satoh, Xiao Zhou, Yinqiang Zheng
CVPR 2022
project page / paper / code / video

This paper first attempts to restore clean GS videos from the RS sensor with the widely ignored global reset feature.

Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion
Yixin Cao Xiang Ji, Xin Lv, Juanzi Li, Yonggang Wen , Hanwang Zhang
ACL 2021   Oral Presentation
paper / code

We present InferWiki, a Knowledge Graph Completion (KGC)dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns.

Educations and Experiences
National Institute of Informatics (NII), Tokyo, Japan
Nov. 2023 - Sep. 2024, Research Assistant, Echizen Laboratory, Information and Society Research Division

The University of Tokyo, Tokyo, Japan
Oct. 2021 - Sep. 2024, Ph.D Student, Graduate School of Information Science and Technology
  • Advisor: Prof. Yinqiang Zheng

Nanyang Technological University, Singapore
Oct. 2019 - May 2021, Research Assistant (Full-time), School of Computer Science and Engineering
  • Advisor: Prof. Yixin Cao and Hanwang Zhang
Services
Reviewer: ICCV, CVPR, ECCV, ICLR, ICML, NeurIPS, ACM MM, AAAI, ACM Computing Surveys, TIP, TPAMI
Volunteer: ICCV 2023


Website template comes from Jon Barron
Last update: October, 2024