I am a senior research scientist at Adobe Research working on MLLM for image/video generation and editing. I was a computer vision engineer working at Apple Vision Pro. I did my PhD advised by Vishal M. Patel.
[CV] [Linkedin][Google Scholar][Github][Twitter]
Research Intern Hiring for Summer 2026 : Please feel free to contact me if you are interested in working with me on a research project in Multi-Model Foundational Model.
Adobe University collaboration: feel free to email me, if you share similar interests in editing for images, videos and texts!
I turn research into high-quality products through data–model co-design, leading features that power Adobe’s portfolio across the pre-GenAI (such as Select Subject) and post-GenAI era (such as Harmonize and Reference Image)
News:
07/25: Harmonize is shipped to Adobe Products with many media coverages:
The Verge, TechCrunch, Forbes, CNET, ZDNET, Creative Bloq, Digital Camera World
07/25: OmniVCus is released.
07/25: Two paper including DiffusionGS accepted in ICCV'25.
06/25: Area Chair for ICLR'26, CVPR'26 , WACV'26.
04/25: Object Insertion is demoed on Adobe Summit: link
03/25: Update Select Subject is released
02/25: Four paper including Unireal accepted in CVPR'25.
02/25: Diffusion Model-Based Image Editing: A Survey got accepted in T-PAMI.
01/25: OS-refinement and Relighting-GS got accepted in ICLR'25.
12/24: Text2Relight got accepted in AAAI'25.
11/24: Our composition prototype is demoed at Max Sneak 2024.
07/24: Generative Portrait Shadow Removal got accepted in Siggraph Asia'24.
07/24: Two paper got accepted in ECCV'24.
02/24: Three paper got accepted in CVPR'24. Relightful Harmonization, Relighting Nerf and Object Stitch V2.
07/23: Photoswap: Personalized subject swapping in images is accepted in NeurIPS'23.
07/23: Perceptual Artifacts Localization for Image Synthesis Tasks is accepted in ICCV'23.
03/23: Rethinking portrait matting with privacy preserving is accepted in IJCV
(International Journal of Computer Vision)
02/23: Three paper got accepted in CVPR'23 on Relighting, Harmonization and Shadow/reflection synthesis.
01/23: Interactive Portrait Harmonization got accepted in ICLR 2023. Check out the project page.
11/22: Select Subject Cloud shipped in Photoshop (Link)
11/22: Semi-supervised Domain Alignment Learning for Single Image Dehazing got accepted in IEEE Transections on Cybernetics.
07/22: One paper got accepted in ECCV'2022.
05/22: Best Paper Award !! "Image De-Raining Using a Conditional Generative Adversarial Network" receives the 2022 IEEE Transactions on Circuits and Systems for Video Technology Best Paper Award.
03/22: Two paper got accepted at CVPR'2022. 1. Lite Vision Transformer with Enhanced Self-Attention 2. Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation
07/21: SSH: A Self-Supervised Framework for Image Harmonization is accepted in ICCV'2021
03/21: MGMatting is accepted in CVPR'2021. Our dataset and code can be found in the link.
