OutDreamer couples a diffusion transformer with mask-driven self-attention and a latent alignment loss to outpaint videos in a zero-shot manner, exceeding prior zero-shot baselines on standard benchmarks.
Free-form video inpainting with 3d gated convolution and temporal patchgan
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
OutDreamer: Video Outpainting with a Diffusion Transformer
OutDreamer couples a diffusion transformer with mask-driven self-attention and a latent alignment loss to outpaint videos in a zero-shot manner, exceeding prior zero-shot baselines on standard benchmarks.