Warping reference tokens' positional encodings into the target view, with depth offsets and frame-level compression fixes, improves geometry-aware camera control in video diffusion transformers.
hub
Title resolution pending
1 Pith paper cite this work, alongside 1,128 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1,128
external citations · OpenAlex
hub tools
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PE-Field 4D: Video Generation Models as Canvas
Warping reference tokens' positional encodings into the target view, with depth offsets and frame-level compression fixes, improves geometry-aware camera control in video diffusion transformers.