Matheus is a researcher interested in all things related to 3D. His work is focused on models and representations of tridimensional data for both discriminative and generative models with a particular interest in learning directly from images.

Matheus received his Ph.D. from University of Massachusetts – Amherst while being supervised by Rui Wang and Subhransu Maji. Before that, he got his M.Sc. and B.Sc. degrees in Computer Science from the Federal University of Rio Grande do Norte (UFRN) in his hometown of Natal, Brazil.

A full list of his publications and more information about his research can be found at his personal website.


GEM3D: Generative Medial Abstractions for 3D Shape Synthesis

Petrov, D., Goyal, P., Thamizharasan, V., Kim, V., Gadelha, M., Averkiou, M., Chaudhuri, S., Kalogerakis, E. (Jul. 25, 2024)


Learning Continuous 3D Words for Text-to-Image Generation

Cheng, T., Gadelha, M., Groueix, T., Fisher, M., Měch, R., Markham, A., Trigoni, N. (Jun. 19, 2024)

CVPR 2024

Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models

Cai, S., Ceylan, D., Gadelha, M., Huang, C., Wang, T., Wetzstein, G. (Jun. 17, 2024)

CVPR 2024

Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D

Pandey, K., Guerrero, P., Gadelha, M., Hold-Geoffroy, Y., Singh, K., Mitra, N. (Jun. 17, 2024)

CVPR 2024