RoPEMover extends 2D RoPE to a depth-aware version in diffusion transformers to enable consistent object relocation in single images, trained mostly on synthetic data with minimal real supervision and claiming SOTA results.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RoPEMover: Depth-Aware Object Relocation via Positional Embeddings
RoPEMover extends 2D RoPE to a depth-aware version in diffusion transformers to enable consistent object relocation in single images, trained mostly on synthetic data with minimal real supervision and claiming SOTA results.