About Me

I'm a research scientist at Adobe. I received my PhD in machine learning under James Hays at the Georgia Institute of Technology, where I also received my BS and MS degrees in computer science. My research interest lies in the intersection of computer vision and machine learning. In particular, I'm interested in controllable image/video generation and multimodal learning.


Previously, I was a research intern at Adobe (2x under Tobias Hinz, 1x under John Collomosse and Zhe Lin), research intern & student researcher at Google (1x under Aaron Sarna, 1x under Andrew Gallagher), and a visiting student at the Max Planck Institute for Intelligent Systems under Andreas Geiger. I was awarded the Marshall D. Williamson Fellowship during my Master's.


Prospective interns: Please email me your CV and brief description of what you'd like to work on.


Publications

MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation

Jinbo Xing, Long Mai, Cusuh Ham, Aniruddha Mahapatra, Chi-Wing Fu, Tien-Tsin Wong, Feng Liu | SIGGRAPH Conference Proceedings 2025

Project page


Personalized Residuals for Concept-Driven Text-to-Image Generation

Cusuh Ham, Matthew Fisher, James Hays, Nicholas Kolkin, Yuchen Liu, Richard Zhang, Tobias Hinz | CVPR 2024

Project page


Modulating Pretrained Diffusion Models for Multimodal Image Synthesis

Cusuh Ham, James Hays, Jingwan Lu, Krishna Kumar Singh, Zhifei Zhang, Tobias Hinz | SIGGRAPH Conference Proceedings 2023

Project page | MarkTechPost article


CoGS: Controllable Generation and Search from Sketch and Style

Cusuh Ham*, Gemma Canet Tarrés*, Tu Bui, James Hays, Zhe Lin, John Collomosse | ECCV 2022

Project page


Density of States Estimation for Out-of-Distribution Detection

Warren R. Morningstar, Cusuh Ham, Andrew G. Gallagher, Balaji Lakshminarayanan, Alexander A. Alemi, Joshua V. Dillon | AISTATS 2021 (oral)

arXiv


Automatic Differentiation Variational Inference with Mixtures

Warren R. Morningstar, Sharad M. Vikram, Cusuh Ham, Andrew G. Gallagher, Joshua V. Dillon | AISTATS 2021

arXiv


ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging

Samarth Brahmbhatt, Cusuh Ham, Charles C. Kemp, James Hays | CVPR 2019 (oral)

Project page | Blog post


Learning to Generate Textures on 3D Meshes

Amit Raj, Cusuh Ham, Connelly Barnes, James Hays, Vladimir Kim, Jingwan Lu | CVPR Deep Generative Models for 3D Understanding 2019 (best paper)

Paper | Workshop page


Variational Image Inpainting

Cusuh Ham*, Amit Raj*, Vincent Cartillier*, Irfan Essa | NeurIPS Bayesian Deep Learning 2018

Paper | Workshop page


Compositional Generation of Images

Amit Raj*, Cusuh Ham*, Huda Alamri*, Vincent Cartillier*, Stefan Lee, James Hays | NeurIPS Visually-Grounded Interaction and Language 2017

Paper | Workshop page


The Sketchy Database: Learning to Retrieve Badly Drawn Bunnies

Patsorn Sangkloy, Nathan Burnell, Cusuh Ham, James Hays | SIGGRAPH 2016

Project page | New Scientist article | Smithsonian article

Teaching
  • CS 4476 / 6476
    • Spring 2022, head TA
    • Fall 2017
    • Fall 2016
  • CS 4476
    • Fall 2019, head TA
  • CS 6476
    • Spring 2021, head TA
    • Spring 2019 (OMS CS)
    • Fall 2018, head TA
CS 7476
  • Spring 2018