Sparkle supplies a large-scale dataset and benchmark for instruction-driven video background replacement, enabling models that generate more natural and temporally consistent new scenes than earlier approaches.
Instructx: Towards unified visual editing with mllm guidance.https://arxiv.org/abs/2510.08485
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.
Introduces TRACE-Edit dataset and evaluation protocol demonstrating semantic degradation of structural variables during VLM-to-DiT alignment in flow-matching video editors.
LIVEditor-14B applies a new sparse attention method (ISA) that prunes context and uses query-sharpness routing to cut attention latency ~60% with no loss in editing quality on standard benchmarks.
InsEdit adapts a video diffusion backbone for text-instruction video editing via Mutual Context Attention, achieving SOTA open-source results with O(100K) data while also supporting image editing.
citing papers explorer
-
VideoCoF: Unified Video Editing with Temporal Reasoner
VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.