About

Hi, I am Jian (James) Wang, currently a Staff Research Scientist at Snap Inc. I am now leading the Snap Research NYC team. I obtained my Ph.D. degree from Carnegie Mellon University, advised by Prof. Aswin Sankaranarayanan and Prof. Srinivasa Narasimhan.
I'm mainly interested in Computational Photography/Imaging, including image/video quality enhancement, image/video editing/manipulation, and generations. I was managed by Shree K. Nayar and Guru Krishnan in Snap. Shree gave a nice keynote about our (unpublished) work in ICCP 2022 which includes my works, see here video link.
I am looking for academic collaborations; if you are interested in working with me on academic research in Computational Imaging, Computational Photography and Computer Vision, please contact me via email by including your CV. 我可以给你提供学术指导和学术ideas.
   X (Twitter): @_JianWang_
Contact: jianwang.cmu at gmail dot com, jwang4 at snapchat dot com; 微信: jianwang8973

News

  • I gave a keynote talk on CVPR 2024 MIPI workshop titled "Towards A Better Camera in the App and AR Glass".
  • I serve as an Area Chair for NeurIPS 2025, ICML2025, ICLR 2025, CVPR 2025, NeurIPS 2024.
  • Magic AR Mirror got the Best Paper Award in SIGGRAPH Asia 2024.
  • We are organizing ECCV 2024 workshop "3DVeComm", 3D Vision and Modeling Challenges in eCommerce link.
  • I gave a poster, Towards a Better Camera, to briefly introduce our work (of one year ago) in CVPR 2024 AC workshop; see here.
  • 🔥🔥 We have multiple openings for internship in 2024 (Summer, Fall or Spring), see flyer. If you are interested, please send me an email. For international students outside of the US, we can help them apply for J-1 visas.
    • Why intern with us? — We have exciting and real research problems from our product Snapchat App (a multimedia instant messaging app with 406 million daily active users, Q3, 2023) and future product Snap Spectacles, our industry-leading AR glasses. We are responsible for every intern by carefully designing each project to fulfill the intern's interest and expected outcome from the internship. The intern has a chance to have product impact, academic impact, or both. In the past five years, each intern had one first-author paper in top-tier conferences 🤗. Besides, interns will have a competitive salary and housing stipend, and have the opportunities to visit many internet celebrity check-in places in New York City 😀. The internship experience could also help students later find full-time jobs in the US.
    • In the past, our group were fortunate to host a group of talented students. They had great experiences and outcomes.
      • 2022, to be updated
      • 2021, 1 CVPR22 Oral by Fangzhuo Mu, 1 ICCP22 best demo award, 1 ECCV22, 1 ACM MM22, 1 journal in submission, 1 US patent
      • 2020, 1 CVPR21 Oral, 1 BOE (journal), 1 CHI21 by Chang Xiao, 3 US patents, 1 tech transfer
      • 2019, 1 US Patent which becomes a key module in current product by Wenzheng Chen and Yingsi Qin (and FTEs), 1 NeurIPS20
      • 2018, 1 best paper award in ACM MM20 by Arun Asokan Nair, 1 Siggraph19 by Chang Xiao, 2 ICCV19 including one oral
      • Dejia Xu (2022), Riku Arakawa (2022), Sizhuo Ma (2020), and Xiao Chang (2019) received the pretigious Snap Research Fellowship. Sizhuo joined Snap Research after graduation.
  • I will serve as an Area Chair for ICLR 2024, CVPR 2024.
  • We are organizing ICCV 2023 workshop "3DVeComm", 3D Vision and Modeling Challenges in eCommerce link.
  • I gave a poster, Towards a Better Camera, to briefly introduce our work (of one year ago) in CVPR 2023 AC workshop; see here.
  • B站GAMES204计算成像上的talk，介绍Snap research在计算成像和计算摄影方面的研究工作 链接
  • 2022 Snap Research Fellowship Winners and Honorable Mentions link are out! Congratulations to all recipients!
  • I will give a talk titled "Computational Imaging/Photography research at Snap Research" at New York University and Purdue University in November and December 2022, respectively.
  • I will serve as an Area Chair for CVPR 2023.
  • Transparent Camera got Best Poster Award in ICCP 2022.

Products

  • We have 5 feature launches in 2024.
  • We had 20 feature launches from 2018 to 2023.

Publications*

* means equal contribution, (co-)corresponding authors, or co-authors are my student advisees
(Note these materials are for timely dissemination of scholarly and technical work. Copyright is retained by the authors or publishers, and reproduction is subject to their terms and constraints. Explicit permission is typically required for reposting.)
2024
Perspective-Aligned AR Mirror with Under-Display Camera
Jian Wang*, Sizhuo Ma, Karl Bayer, Yi Zhang, Peihao Wang, Bing Zhou,
Shree Nayar, Gurunandan Krishnan
Siggraph Asia, 2024 (Journal) (Best Paper Award)
InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention
Howard Zhang+, Yuval Alaluf+, Sizhuo Ma, Achuta Kadambi, Jian Wang*, Kfir Aberman*
arXiv, 2024
Clearer Frames, Anytime: Resolving Velocity Ambiguity in Video Frame Interpolation
Zhihang Zhong, Gurunandan Krishnan, Xiao Sun, Yu Qiao, Sizhuo Ma*, Jian Wang*
ECCV, 2024 (Oral)
Delving Deep into Engagement Prediction of Short Videos
Dasong Li, Wenjie Li, Baili Lu, Hongsheng Li, Sizhuo Ma, Gurunandan Krishnan, Jian Wang*
ECCV, 2024
Holodepth: Programmable Depth-Varying Projection via Computer-Generated Holography
Dorian Chan, Matthew O'Toole, Sizhuo Ma, Jian Wang
ECCV, 2024
Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior
Baiang Li, Sizhuo Ma, Yanhong Zeng, Xiaogang Xu,
Youqing Fang, Zhao Zhang, Jian Wang*+ (lead), Kai Chen*
arXiv, 2024
DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs
Zhixiang Wang, Yu-Lun Liu, Jia-Bin Huang, Shin'ichi Satoh, Sizhuo Ma, Guru Krishnan, Jian Wang*
IJCV, 2024
Learning to Recover Spectral Reflectance from RGB Images
Dong Huo, Jian Wang, Yiming Qian, Yee-Hong Yang
IEEE Transactions on Image Processing (TIP), 2024
Matting by Generation
Zhixiang Wang, Baiang Li, Jian Wang*, Yu-Lun Liu, Jinwei Gu, Yung-Yu Chuang, Shin'ichi Satoh
Siggraph, 2024
DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer
Wei-Ting Chen, Gurunandan Krishnan, Qiang Gao, Sy-Yen Kuo, Sizhuo Ma*, Jian Wang*+ (+ project lead)
CVPR, 2024
RobustSAM: Segment Anything Robustly on Degraded Images
Wei-Ting Chen, Yu-Jiet Vong, Sy-Yen Kuo, Sizhuo Ma*, Jian Wang*
CVPR, 2024 (Highlight)
DiffBody: Human Body Restoration by Imagining with Generative Diffusion Prior
Yiming Zhang, Zhe Wang, Xinjie Li, Yunchen Yuan,
Chengsong Zhang, Xiao Sun, Zhihang Zhong*, Jian Wang*
arXiv, 2024
Robust Structured Light with Efficient Redundancy Codes
Zhanghao Sun, Xinxin Zuo, Dong Huo,
Yu Zhang, Yiming Qian, and Jian Wang* (* corresponding author)
Optics Express, 2024
Copy or Not? Reference-Based Face Image Restoration with Fine Details
Min Jin Chong, Dejia Xu, Yi Zhang, Zhangyang Wang, David Forsyth, Gurunandan Krishnan, Yicheng Wu, Jian Wang
WACV, 2025
Towards 4D Human Video Stylization
Tiantian Wang*, Xinxin Zuo+, Fangzhuo Mu+, Jian Wang*, Ming-Hsuan Yang
arXiv, 2024
NTIRE 2024 Challenge on Stereo Image Super-Resolution: Methods and Results
Longguang Wang, ..., Jian Wang, Yuqi Miao, Baiang Li, Kejie Zhao, ...
CVPRW, 2024
Report available soon
MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Result
Yuekun Dai, ..., Jian Wang, Yuqi Miao, Baiang Li, Gang Wei, ...
CVPRW, 2024
2023
Personalized Restoration via Dual-Pivot Tuning
Pradyumna Chari, Sizhuo Ma, Daniil Ostashev, Achuta Kadambi, Gurunandan Krishnan,
Jian Wang*, Kfir Aberman
arXiv, 2023
Light Codes for Fast Two-Way Human-Centric Visual Communication
Mohit Gupta, Jian Wang, Karl Bayer, Shree Nayar
ACM TOG, 2023 (Presented in Siggraph, 2024)
N-euro Predictor: A Neural Network Approach for Smoothing and Predicting Motion Trajectory
Qijia Shao*, Jian Wang*, Bing zhuo,
Vu An Tran, Gurunandan Krishnan, Shree Nayar
IMWUT/UbiComp, 2023 (Oral) (Best Teaser Award)
Energy-Efficient Adaptive 3D Sensing
Brevin Tilmon, Zhanghao Sun, Sanjeev J. Koppal, Yicheng Wu, Georgios Evangelidis, Ramzi Zahreddine, Gurunandan Krishnan, Sizhuo Ma*, Jian Wang*
CVPR, 2023
QfaR: Location-Guided Scanning of Visual Codes from Long Distances
Sizhuo Ma, Jian Wang, Wenzheng Chen,
Suman Banerjee, Mohit Gupta, Shree Nayar
MobiCom, 2023 (Oral)
A Unified Conditional Framework for Diffusion-based Image Restoration
Yi Zhang, Xiaoyu Shi, Dasong Li,
Xiaogang Wang, Jian Wang*, Hongsheng Li*
NeurIPS, 2023
Glass Segmentation with RGB-Thermal Image Pairs
Dong Huo*, Jian Wang*,
Yiming Qian, and Yee-Hong Yang
IEEE Transactions on Image Processing (TIP), 2023
Be Real in Scale: Swing for True Scale in Dual Camera Mode
Rui Yu, Jian Wang, Sizhuo Ma, Sharon X. Huang, Gurunandan Krishnan, Yicheng Wu
ISMAR, 2023
Image Harmonization with Diffusion Model
Jiajie Li, Jian Wang, Chen Wang, Jinjun Xiong
arXiv, 2023
2022
3D Photo Stylization:
Learning to Generate Stylized Novel Views from a Single Image
Fangzhuo Mu, Jian Wang*,
Yicheng Wu*, and Yin Li*
CVPR, 2022 (Oral)
Cloud2Sketch: Augmenting Clouds with Imaginary Sketches
Zhaoyi Wan, Dejia Xu, Zhangyang Wang,
Jian Wang*, and Jiebo Luo* (* co-corresponding authors)
ACM MM, 2022
Privacy-Preserving Visual Localization with Event Cameras
Junho Kim, Young Min Kim, Yicheng Wu, Ramzi Zahreddine,
Weston A. Welge, Gurunandan Krishnan, Sizhuo Ma*, Jian Wang*
arXiv, 2022
Transparent Camera
Jian Wang, Zhanghao Sun,
Dejia Xu, Mr./Ms. Cool +
(+ call for awesome collaborators (like Sony, Samsung) to make it happen)
Presented as a poster in ICCP 2022 (Best Poster Award)
RobustPPG: Camera-Based Robust Heart Rate Estimation Using Motion Cancellation
Akash Kumar Maity*, Jian Wang*,
Ashutosh Sabharwal, Shree Nayar
Biomedical Optics Express, 2022
Seeing Far in the Dark with Patterned Flash
Zhanghao Sun*, Jian Wang*, Yicheng Wu, Shree Nayar
ECCV, 2022
(Survey) Recent Progress in Computational Imaging
计算成像前沿进展
Xiong Dun*, Qiang Fu*, Haotian Li*, Tiancheng Sun*, Jian Wang*, and Qilin Sun*
Journal of Image and Graphics, 中国图象图形学报, 2022
A Clustering-based Method for Estimating Pennation Angle from B-mode Ultrasound Images
Xuefeng Bao, Qiang Zhang, Natalie Fragnito,
Jian Wang, Nitin Sharma
Wearable Technologies, 2022
2021
Seeing in Extra Darkness Using a Deep-red Flash
Jinhui Xiong*, Jian Wang*,
Wolfgang Heidrich, and Shree Nayar
CVPR 2021 (Oral)
2020
Group Contextual Encoding for 3D Point Clouds
Xu Liu, Chengtao Li, Jian Wang,
Jingbo Wang, Boxin Shi, and Xiaodong He
NeurIPS 2020
Dense Point Diffusion for 3D Object Detection
Xu Liu, Jiayan Cao, Qianqian Bi,
Jian Wang, Boxin Shi, and Yicheng Wei
3DV 2020
2019
Micro-Baseline Structured Light
Vishwanath Saragadam*, Jian Wang, Mohit Gupta, and Shree Nayar
ICCV 2019
Agile Depth Sensing Using Triangulation Light Curtains
Joseph R. Bartels, Jian Wang,
William “Red” Whittaker1, and Srinivasa G. Narasimhan
ICCV 2019 (Oral)
Stereoscopic Dark Flash for Low-light Photography
Jian Wang, Tianfan Xue, Jonathan T. Barron, and Jiawen Chen
ICCP 2019 (Oral)
Before PhD graduation

High Resolution 2D Imaging and 3D Scanning with Line Sensors
Jian Wang
PhD Thesis, Carnegie Mellon University, 2018
Programmable Triangulation Light Curtains
Jian Wang, Joe Bartels, William Whittaker,
Aswin C. Sankaranarayanan, and Srinivasa G. Narasimhan
ECCV 2018 (Oral)
Reflectance Capture using Univariate Sampling of BRDFs
Zhuo Hui, Kalyan Sunkavalli, Joon-Young Lee, Sunil Hadap,
Jian Wang, and Aswin C. Sankaranarayanan
ICCV 2017
Compressive Spectral Anomaly Detection
Vishwanath Saragadam, Jian Wang,
Xin Li, and Aswin C. Sankaranarayanan
ICCP 2017 (Oral)
Dual Structured Light Using a 1D Sensor
Jian Wang, Aswin C. Sankaranarayanan,
Mohit Gupta, and Srinivasa G. Narasimhan
ECCV 2016 (Oral)
Radon Transform Imaging: Low cost video compressive sensing at extreme resolutions
Aswin C. Sankaranarayanan, Jian Wang, and Mohit Gupta
SPIE Imaging conference 2016
Reconstruction Free Inference from Compressive Measurements
Suhas Lohit, Kuldeep Kulkarni, Pavan Turaga,
Jian Wang, and Aswin C. Sankaranarayanan
CCD 2015 (Oral) (Best Paper Award)
LiSens — A Scalable Architecture for Video Compressive Sensing
Jian Wang, Mohit Gupta, and Aswin C. Sankaranarayanan
ICCP 2015 (Oral)
Photometric Stereo with Small Angular Variations
Jian Wang, Yasuyuki Matsushita,
Boxin Shi, and Aswin C. Sankaranarayanan
ICCV 2015
Gigapixel 3D Camera
Jian Wang, Xiao Liang, Yasuyuki Matsushita,
Magnetro Chen, and Bojun Huang
Tech-report 2015
Design of Control Algorithms for Smart Car Based on Vision
Jian Wang, Xiaowei Zhang, Jin Yang,
Xin Zan, and Xiaoyong Liu
Microcomputer and Its Applications, 2010
First-Class Award (Top 5.6%) and Excellent Paper Award (Top 4.2%) in National Competition

Patents

  • US patent, 2022, (confidential)
  • US patent, 2022, (confidential)
  • US patent, 2022, “Location-guided Scanning of Visual Codes”, Sizhuo Ma, Jian Wang, Mohit Gupta, Shree K. Nayar. [link]
  • US patent, 2022, “Apparatus Having A Viewfinder Mirror Configuration”, Shree K. Nayar, Jian Wang. [link]
  • US patent, 2022, “Long Distance QR Code Decoding”, Shree K. Nayar, Jian Wang, Wenzheng Chen. [link]
  • US patent, 2022, “Agile Depth Sensing Using Triangulation light Curtains”, Srinivasa G. Narasimhan, Joseph Bartels, William Whittaker, Jian Wang. [link]
  • US patent, 2021, “Programmable Light Curtains”, Srinivasa G. Narasimhan, Jian Wang, Aswin C. Sankaranarayanan, Joseph Bartels, William Whittaker. [link]
  • US patent, 2020, (filed anonymously, confidential)
  • US patent, 2019, “Dark Flash Photography with a Stereo Camera”, Tianfan Xue, Jian Wang, Jiawen Chen, Jonathan T. Barron. [link]
  • US patent, 2017, “Apparatus and Methods for Video Foreground Background Segmentation with Multi-View Spatial Temporal Graph Cuts”, Jinwei Gu, Jian Wang, Wei Jiang. [link]
  • CN patent, 2014, “Ground Target Positioning Method Applied into Video Monitoring System”, CN102359780 B, Zonghai Chen, Zhiling Wang, Yuzhuo Zhao, Mingwei Guo, Jian Wang. [link] [pdf] [pdf_Eng]
  • CN patent, 2012, “Real-time Identity Recognition and Authentication Method for Self-service Equipment System of Bank”, CN102364527 A, Jian Wang, Zhiling Wang, Yuzhuo Zhao, Mingwei Guo, and Zonghai Chen. [link] [pdf] [pdf_Eng]
  
             Last updated on May 2024. Please let me know if you find a dead link. Thanks!