Autoregressive Generation of Static and Growing Trees

We propose a transformer architecture and training strategy for tree generation. The architecture processes data at multiple resolutions and has an hourglass shape, with middle layers processing fewer tokens than outer layers. Similar to convolutional networks, we introduce longer-range skip connections to complement this multi-resolution approach. The key advantages of this architecture are the faster processing speed and lower memory consumption. We are, therefore, able to process more complex trees than would be possible with a vanilla transformer architecture. Furthermore, we extend this approach to perform image-to-tree and point-cloud-to-tree conditional generation and to simulate the tree growth processes, generating 4D trees. Empirical results validate our approach in terms of speed, memory consumption, and generation quality.

@Article{Wang2025_tree_generation,
	author   = {Wang, Hanxiao and Zhang, Biao and Klein, Jonathan and Michels, Dominik L. and Yan, Dong-Ming and Wonka, Peter},
	title    = {Autoregressive Generation of Static and Growing Trees},
	journal  = {ACM Transactions on Graphics (SIGGRAPH Asia)},
	year     = {2025},
	month    = {12}
	doi      = {10.1145/3757377.3763818},
}