Yifan Jiang

Yifan Jiang

Ph.D student at University of Texas at Austin
Email: yifanjiang97 At utexas Dot edu
About

Hi, I am Yifan Jiang (江亦凡), a fourth-year Ph.D student at University of Texas at Austin, VITA Group, supervised by Prof. Zhangyang (Atlas) Wang. Before that I spent one year at Texas A&M University. I received my bachelor's degree from Huazhong University of Science and Technology, Wuhan, China. I've interned at Adobe (Marc Levoy's team), Google Research (GCam), Adobe (Applied Research Team), and Bytedance AI Lab (US CV Lab).

I spent most of my time tackling problems in the area of computational photography and generative models. I'm also interested at building efficient tools to accelerate these algorithms for real products. I believe in the future of metaverse/omniverse, and that also reflects my current research interests: which gradually shift from discriminative task to creative vision, from pure 2D vision to the collaboration of 2D and 3D vision.

News: I received Apple PhD Fellowship 2023.

Publications
( show selected / show all by date / show all by topic )

Topics: Neural Rendering / Generative Model / Computational Photography / Others / (*: indicates equal contribution.)

NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° Views
Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Yi Wang, Zhangyang Wang
[Paper] [Project Page] [Code]
AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training
Yifan Jiang, Peter Hedman, Ben Mildenhall, Dejia Xu, Jonathan T. Barron, Zhangyang Wang, Tianfan Xue
[Paper] [Project Page]
NeRF-SOS: Any-view Self-supervised Object Segmentation on Complex Real-world Scenes
Zhiwen Fan, Peihao Wang, Yifan Jiang, Xinyu Gong, Dejia Xu, Zhangyang Wang
[Paper] [Project Page] [Code]
Signal Processing for Implicit Neural Representations
Dejia Xu*, Peihao Wang*, Yifan Jiang, Zhiwen Fan, Zhangyang Wang
[Paper] [Project Page] [Code]
ReCoRo: Region-Controllable Robust Light Enhancement with User-Specified Imprecise Masks
Dejia Xu, Hayk Poghosyan, Shant Navasardyan, Yifan Jiang, Humphrey Shi, Zhangyang Wang
[Paper] [Code]
Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN
Qiucheng Wu*, Yifan Jiang*, Junru Wu*, Kai Wang, Gong Zhang, Huphery Shi, Zhangyang Wang, Shiyu Chang
[Paper] [Project Page] [Code]
Unified Implicit Neural Stylization
Yifan Jiang*, Zhiwen Fan*, Peihao Wang*, Xinyu Gong, Dejia Xu, Zhangyang Wang
[Paper] [Project Page] [Code]
SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image
Yifan Jiang*, Dejia Xu*, Peihao Wang, Zhiwen Fan, Humphery Shi, Zhangyang Wang
[Paper] [Project Page] [Code]
VAQF
VAQF: Fully Automatic Software-hardware Co-design Framework for Low-bit Vision Transformer
Mengshu Sun, Haoyu Ma, Guoliang Kang, Yifan Jiang, Tianlong Chen, Xiaolong Ma, Zhangyang Wang, Yanzhi Wang
[Paper]
MalleConv
Fast and High-Quality Image Denoising via Malleable Convolutions
Yifan Jiang, Bartlomiej Wronski, Ben Mildenhall, Jonathan T. Barron, Zhangyang Wang, Tianfan Xue
[Paper] [Project]
AutoX3D
Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search
Yifan Jiang*, Xinyu Gong*, Junru Wu, Humphery Shi, Zhicheng Yan, Zhangyang Wang
[Paper]
CERL
CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise
Zeyuan Chen, Yifan Jiang, Dong Liu, Zhangyang Wang
[Paper] [Code]
TransGAN
TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
Yifan Jiang, Shiyu Chang, Zhangyang Wang
[Paper] [Code]
Covered Media: [Youtube Video] [机器之心] [青源 Live] [Quanta Magazine]
IA-RED^2
IA-RED^2: Interpretability-Aware Redundancy Reduction for Vision Transformers
Bowen Pan, Rameswar Panda, Yifan Jiang, Zhangyang Wang, Rogerio Feris, Aude Oliva
[Paper]
SSH
SSH: A Self-Supervised Framework for Image Harmonization
Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, Zhangyang Wang
[Paper] [Code]
InstantNet
InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
Yonggan Fu, Zhongzhi Yu, Yongan Zhang, Yifan Jiang, Chaojian Li, Yongyuan Liang, Mingchao Jiang, Zhangyang Wang, Yingyan Lin
[Paper] [Code]
ISTA
A Design Space Study for LISTA and Beyond
Tianjian Meng*, Xiaohan Chen*, Yifan Jiang, Zhangyang Wang
[Paper] [Code]
AutoGAN
AutoGAN: Neural Architecture Search Meets Generative Adversarial Networks
Xinyu Gong, Shiyu Chang, Yifan Jiang, Zhangyang Wang
[Paper] [Code]
Covered Media: [Synced AI Review]
EnlightenGAN
EnlightenGAN: Deep Light Enhancement without Paired Supervision
Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang
[Paper] [Code] [Supplementary]
PS-GAN
Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
Xi Ouyang, Yu Cheng, Yifan Jiang, Chun-Liang Li, Pan Zhou
[Code] [Paper]

Click to show [Full Publications]



Service
  • Reviewer or program committee member for CVPR'2021-2023, ICCV'2021, ECCV'2022, ICML'2022-2023, NeurIPS'2022, ICLR'2023, Siggraph'2022, Siggraph Aisa'2022, WACV'2022, IJCAI'2023, IEEE Transaction on Image Processing (TIP), IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), International Journal of Computer Vision (IJCV), NeuroComputing, IEEE Transactions on Computational Imaging (TCI).
  • Workshop Organizer for ECCV RLQ-TOD Workshop 2020
    • Invited Talk
  • [Jan 2023] "Learning to Enhance Low-light Images without Paired Supervision" at [IEEE SPS Webinar], after my TIP work EnlightenGAN was hilighted as one of SPS's top-25 most downloaded articles on IEEE Xplore®, 2021-2022
  • [Jan 2022] "Fast and High Quality Image Denoising via Malleable Convolution" at Adobe, NextCam.
  • [July 2021] "Vision Transformer for Image Generation, Editing, and Processing" at Google Research, GCam.
  • [Mar 2021] "TransGAN: Two Transformers Can Make One Strong GAN, and That Can Scale Up." at [机器之心], [智源社区], [cai-workshop], University of Oregon





    • The website template was originally borrowed from [1], then further optimized from [2],[3]. Thanks to these guys!