I am a Research Scientist at Adobe Research London working on image/3D/video generative modeling.
I received my PhD in Computer Science from King Abdullah University of Science and Technology working with Prof. Peter Wonka.
I'm broadly interested in computer graphics, especially image, 3D and video synthesis and generative modeling techniques. My research involves the generation end editing of large-scale images using deep neural networks, focusing on the quality of the generated content, controllability and the plausible compositing of the output.
In my spare time, I enjoy designing, building, creating, disassembling and assembling things. I love to be outdoors, play music, learn languages and explore the world.
The code for our ECCV paper SuperGaussian has been published on Github.
Our paper “SuperGaussian: Repurposing Video Models for 3D Super Resolution” was accepted to ECCV 2024. This project was led by Adobe intern Yuan Shen, who was co-mentored by myself and several other amazing Adobe researchers.
I will be serving on the SIGGRAPH Asia 2024 Technical Papers Committee.
Our paper “IntrinsicDiffusion: Joint Intrinsic Layers from Latent Diffusion Models” was accepted to SIGGRAPH 2024. This paper was led by last summer’s Adobe London intern Jundan Luo.
We are looking for motivated interns for the Summer of 2024 to join us in the Adobe LondonLab for exciting research projects. Feel free to reach out to me if you are interested or directly apply via the application system.
I am happy to be acknowledged as an Outstanding Reviewer for reviewing for ICCV 2023!
I am excited to share that I have started to work at Adobe London as a Research Scientist as of June 2023.
We have made the code for our CVPR paper VIVE3D available on Github!
I successfully defended my PhD in Computer Science on April 17, 2023! A huge Thank You to my advisor Peter Wonka and my PhD committee consisting of Bernd Bickel, Helmut Pottmann and Bernard Ghanem.
Our paper “VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANs” was accepted to CVPR 2023. This paper is the result of a collaboration with Meta Reality Labs Research.
I was acknowledged as an Outstanding Reviewer at ECCV 2022!
Our paper “On the Robustness of Quality Measures for GANs” was accepted for publication at the European Conference on Computer Vision (ECCV).
I feel honored to be acknowledged as an Outstanding Reviewer at CVPR 2022!
This summer, I will be working at Meta Reality Labs in Sausalito, CA from June to September 2022.
The code for our CVPR paper InsetGAN is now available on Github.
Our paper “InsetGAN for Full-Body Image Generation” was accepted to CVPR 2022. This paper is the result of a collaboration with Adobe Research.
I have been invited by the CEMSE division at KAUST to serve as a Student Ambassador.
Our paper “Large Scale Architectural Asset Extraction from Panoramic Imagery” was accepted for publication in the IEEE Transactions in Visualization and Computer Graphics (TVCG).
I will be working at Adobe in the Creative Intelligence Lab in San José, CA from August to November 2020.
I’ve been awarded a fellowship by Facebook Research, which is designed to encourage and support promising doctoral students engaged in innovative and relevant research in areas related to computer science and engineering.
I will be working at Weta Digital in the Look Dev R&D department in Wellington, NZ from April to June 2020.
I will be supporting my advisor as a teaching assistant in the KAUST course CS390DD Deep Learning for Visual Computing this fall semester.
I was invited to give a talk about my work on image synthesis at IST Austria on September 2.
I will be presenting TileGAN at ACM SIGGRAPH 2019 at the Los Angeles Convention Center on Tuesday, July 30 (session “High Performance Rendering”).
We released the code for TileGAN on Github!
Our paper TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures was accepted as a technical paper at ACM SIGGRAPH 2019.