A single diffusion scene prior over SE(3) object sets can be steered by RL post training, text conditioning, and MCTS search, backed by a new 44 million scene dataset.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Steerable Scene Generation with Post Training and Inference-Time Search
A single diffusion scene prior over SE(3) object sets can be steered by RL post training, text conditioning, and MCTS search, backed by a new 44 million scene dataset.