ContextDrag enables precise drag-based image editing by injecting VAE-encoded reference features at aligned positions and re-encoding positional embeddings to maintain consistency in in-context models like FLUX-Kontext.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
Online3R enables online adaptation of a pretrained geometry foundation model for consistent sequential reconstruction by adding learnable visual prompts trained via local and global consistency constraints.
citing papers explorer
-
ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention
ContextDrag enables precise drag-based image editing by injecting VAE-encoded reference features at aligned positions and re-encoding positional embeddings to maintain consistency in in-context models like FLUX-Kontext.
-
Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Model
Online3R enables online adaptation of a pretrained geometry foundation model for consistent sequential reconstruction by adding learnable visual prompts trained via local and global consistency constraints.