Difan Liu

Research Scientist

San Jose

Difan joined Adobe Research in September 2022.

Before joining Adobe, he obtained his Ph.D. degree at the University of Massachusetts Amherst in 2022 and bachelor’s degree at the University of Science and Technology of China in 2017.

He works in the areas of computer graphics, computer vision and machine learning. In particular, he is interested in the field of generative models, image editing, vector art and 3D graphics.

Check Difan’s webpage to learn more about his research.

Publications

VecFusion: Vector Font Generation with Diffusion

Thamizharasan, V., Liu, D., Agarwal, S., Fisher, M., Gharbi, M., Wang, O., Jacobson, A., Kalogerakis, E. (Jun. 19, 2024)

CVPR Highlight

CVPR 2024

SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model

Li, Z., Kang, Y., Liu, Y., Liu, D., Hinz, T., Liu, F., Wang, Y. (Jun. 19, 2024)

CVPR 2024

AT-EDM: Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models

Wang, H., Liu, D., Kang, Y., Li, Y., Lin, Z., Jha, N., Liu, Y. (Jun. 17, 2024)

CVPR 2024

ASSET: Autoregressive Semantic Scene Editing with Transformers at High Resolutions

Liu, D., Shetty, S., Hinz, T., Fisher, M., Zhang, R., Park, T., Kalogerakis, E. (Aug. 1, 2022)

ACM Transactions on Graphics (TOG)

ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds

Sharma, G., Liu, D., Kalogerakis, E., Maji, S., Chaudhuri, S., Měch, R. (Aug. 24, 2020)

ECCV