| CARVIEW |
At Adobe, I work on computer vision for Imaging products. I am the primary contributor to several features including Instruction-based Image Editing, Select Subject, Object Finder, and Select People Details. I earned my Ph.D. at Arizona State University, advised by Baoxin Li. I have contributed to 8 tech transfers to products including Photoshop, Lightroom, and Stardust.
Now recruiting summer research interns in image/video editing with MLLM.
News
- Feb. 2025 – 3 papers accepted to CVPR 2025
- Jan. 2025 – 1 paper accepted to AAAI 2025
- Nov. 2024 – "Select People Details" featured by Colin Smith on YouTube
Highlighted Research
I strive for simple yet scalable methods in image understanding and editing. Representative works are highlighted below. Full list available on Google Scholar.
OmniStyle: Filtering High Quality Style Transfer Data at Scale
Ye Wang, Ruiqi Liu, Jiang Lin, Zili Yi, Yilin Wang★ Rui Ma★★ co-advisor project page / paper /
CVPR 2025
OmniStyle is the first end-to-end style transfer framework based on the Diffusion Transformer (DiT) architecture, achieving high-quality 1K-resolution stylization by leveraging the large-scale, filtered OmniStyle-1M dataset. It supports both instruction- and image-guided stylization, enabling efficient and versatile style transfer across diverse styles.
FINECAPTION: Compositional Image Captioning
Hang Hua, Qing Liu, Lingzhi Zhang, Jing Shi, Zhifei Zhang, Yilin Wang, Jianming Zhang, Jiebo Luo, Zhe Lin,CVPR 2025
A unified vision-language model for free-form mask grounding and compositional captioning.
UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics
Xi Chen, Zhifei Zhang, He Zhang, Yuqian Zhou, Soo Ye Kim, Qing Liu, Yijun Li, Jianming Zhang, Nanxuan Zhao, Yilin Wang, Hui Ding, Zhe Lin, Hengshuang Zhao 2025 (Highlight)
pdf/
project page
Foundaitional multi-modal generative model UniReal is a universal framework for multiple image generation and editing tasks. We leverage a video model to handld image tasks by treating different numbers of input/output images as frames. We also seek universal supervisions from video data, thus generating realistic results that understand the world dynamics.
SigStyle: Signature Style Transfer via Personalized Text-to-Image Models
Ye Wang, Tongyuan Bai, Xuping Xie, Zili Yi, Yilin Wang★ Rui Ma★★ co-advisor project page / paper /
AAAI 2025
Sigstyle is a style preserved style transfer method via personalized subject editing diffusion model.
SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing
ECCV 2024
Jing Gu, Nanxuan Zhao, Wei Xiong, Qing Liu, Zhifei Zhang, He Zhang, Jianming Zhang, HyunJoon Jung, Yilin Wang★, Xin Eric Wang★
★ Co-advisor
A method for personalized subject driven image editing.
UniHuman: A Unified Model for Editing Human Images in the Wild.
CVPR 2024
Nannan Li, Qing Liu, Krishna Kumar Singh, Yilin Wang, Jianming Zhang, Bryan A. Plummer, Zhe Lin
Human editing via diffusion.
Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion
AAAI (oral) 2024
Bowen Zhang, Qing Liu, Jianming Zhang, Yilin Wang, Akide Liu, Zhe Lin, Yifan Liu
Amodal segmentation considers mutual occlusion.
PHOTOSWAP: Personalized Subject Swapping in Images
NeurIPS 2023
Jing Gu, Yilin Wang, Nanxuan Zhao, Tsu-Jui Fu, Wei Xiong, Qing Liu, Zhifei Zhang, He Zhang, Jianming Zhang, HyunJoon Jung, Xin Eric Wang
A method for personalized subject driven image editing.
LightPainter: Interactive Portrait Relighting with Freehand Scribble
CVPR 2023
Yiqun Mei, He Zhang, Xuaner Zhang, Jianming Zhang, Zhixin Shu, Yilin Wang, Zijun Wei, Yan Shi, HyunJoon Jung, Vishal M. Patel
A scribble-based relighting system that allows users to interactively manipulate portrait lighting effects with ease.
Interactive Portrait Harmonization
ICLR 2023
Jeya Maria Jose Valanarasu, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Yinglan Ma, Zijun Wei, Kalyan Sunkavalli, Vishal M. Patel
Interactive harmonization for portrait photos.
Lite Vision Transformer with Enhanced Self-Attention
CVPR 2022
Chenglin Yang, Yilin Wang, Jianming Zhang, He Zhang, Zijun Wei, Zhe Lin, Alan Yuille
Light-weight vision transformer models for vision tasks.
SSH: A Self-Supervised Framework for Image Harmonization
ICCV 2021
Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, Zhangyang Wang
Image harmonization based on self-supervised learning.
Mask Guided Matting via Progressive Refinement Network
CVPR 2021
Qihang Yu, Jianming Zhang, He Zhang, Yilin Wang, Zhe Lin, Ning Xu, Yutong Bai, Alan Yuille
Mask guided image matting.
Multimodal Contrastive Training for Visual Representation Learning
CVPR 2021
Xin Yuan, Zhe Lin, Jason Kuen, Jianming Zhang, Yilin Wang, Michael Maire, Ajinkya Kale, Baldo Faieta
Intra- and inter-modal similarity preservation for multimodal representation learning.
Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation
ECCV 2020
Kenan E. Ak, Ning Xu, Zhe Lin, Yilin Wang
Shape Adaptor: A Learnable Resizing Module
ECCV 2020
Shikun Liu, Zhe Lin, Yilin Wang, Jianming Zhang, Federico Perazzi, Edward Johns
Multimodal Style Transfer via Graph Cuts
ICCV 2019
Yulun Zhang, Chen Fang, Yilin Wang, Zhaowen Wang, Zhe Lin, Yun Fu, Jimei Yang
PhD Research
2018
- Generalizing Graph Matching beyond Quadratic Assignment Model
Tianshu Yu, Junchi Yan, Yilin Wang, Wei Liu, Baoxin Li
NeurIPS 2018 - Weakly Supervised Facial Attribute Manipulation via Deep Adversarial Network
Yilin Wang, Suhang Wang, Guojun Qi, Jiliang Tang, Baoxin Li
WACV 2018 [paper] - CrossFire: Cross Media Joint Friend and Item Recommendations
Kai Shu, Suhang Wang, Jiliang Tang, Yilin Wang, Huan Liu
WSDM 2018 spotlight [paper] - Understanding and Predicting Delay in Reciprocal Relations
Jundong Li, Jiliang Tang, Yilin Wang, Yali Wan, Yi Chang, Huan Liu
WWW 2018 Research Track [arXiv] - Exploring Hierarchical Structures for Recommender Systems
Suhang Wang, Jiliang Tang, Yilin Wang, Huan Liu
IEEE TKDE
2017
- CLARE: A Joint Approach to Label Classification and Tag Recommendation
Yilin Wang, Suhang Wang, Jiliang Tang, Guojun Qi, Huan Liu, Baoxin Li
AAAI 2017 oral [paper] [code] - Understanding and Discovering Deliberate Self-harm Content in Social Media
Yilin Wang, Jiliang Tang, Jundong Li, Baoxin Li, Yali Wan, Clayton Mellina, Neil O'Hare, Yi Chang
WWW 2017 Research Track [paper] [slides] - Exploiting Hierarchical Structures for Unsupervised Feature Selection
Suhang Wang, Yilin Wang, Jiliang Tang, Charu Aggarwal, Suhas Ranganath, Huan Liu
SDM 2017 [paper] - What Your Images Reveal: Exploiting Visual Contents for Point-of-Interest Recommendation
Suhang Wang, Yilin Wang, Jiliang Tang, Kai Shu, Suhas Ranganath, Huan Liu
WWW 2017 Research Track [paper]
2016
- PPP: Joint Pointwise and Pairwise Image Label Prediction
Yilin Wang, Suhang Wang, Jiliang Tang, Huan Liu, Baoxin Li
CVPR 2016 [paper] - Efficient Unsupervised Abnormal Crowd Activity Detection Based on a Spatiotemporal Saliency Detector
Yilin Wang, Qiang Zhang, Baoxin Li
WACV 2016 [paper] [code] - Scale Adaptive Eigen Eye for Fast Eye Detection in Wild Web Images
Xu Zhou, Yilin Wang, Peng Zhang, Baoxin Li
ICIP 2016
2015
- Sentiment Analysis for Social Media Images
Yilin Wang, Baoxin Li
ICDM PhD Forum 2015 - Real Time Vehicle Back-up Warning System with Single Camera
Yilin Wang, Jun Cao, Baoxin Li
ICIP 2015 [paper] - Unsupervised Sentiment Analysis for Social Media Images
Yilin Wang, Suhang Wang, Jiliang Tang, Huan Liu, Baoxin Li
IJCAI 2015 [paper] [project] - Inferring Sentiment from Web Images with Joint Inference on Visual and Social Cues: A Regulated Matrix Factorization Approach
Yilin Wang, Yuheng Hu, Subbarao Kambhampati, Baoxin Li
ICWSM 2015 oral [paper] - Structure Preserving Image Quality Assessment
Yilin Wang, Qiang Zhang, Baoxin Li
ICME 2015 oral [paper] - Exploring Implicit Hierarchical Structure for Recommender Systems
Suhang Wang, Jiliang Tang, Yilin Wang, Huan Liu
IJCAI 2015 [paper] - Improving Vision-based Self-positioning in Intelligent Transportation Systems via Integrated Lane and Vehicle Detection
Parag S. Chandakkar, Yilin Wang, Baoxin Li
WACV 2015 [paper]
2014
- Image Co-segmentation via Multi-task Learning
Qiang Zhang, Jiayu Zhou, Yilin Wang, Jieping Ye, Baoxin Li
BMVC 2014 [paper]
Service & Interns
- Area Chair: ACM MM 2020, 2021
- Reviewer: CVPR, ICCV, ECCV, ICML, NeurIPS (since 2017)
- Interns collaborated with: Zhanghan Ke,
Nannan Li,
Yiqun Mei ,
Yulun Zhang, Shikun Liu, Chenglin Yang,
Jeya Maria Jose Valanarasu, Kenan E Ak, Qihang Yu,
Xin Yuan , Yifan Jiang, Jing Gu, Zhibo Yang