StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
arXiv preprint arXiv:2311.00213 , year=
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
fields
cs.CV 9representative 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.
A three-stage distillation plus AR mask cache converts a bidirectional DiT editor into a real-time causal streaming editor that preserves non-edited regions at 12.66 FPS.
SteerVTE adds lightweight style and dual-granularity glyph adapters to a frozen video diffusion model, introduces a glyph-aware loss and progressive training, and releases a 1M synthetic dataset to enable accurate video text editing.
RVEDiT improves DiT-based video editing by granularity-routed token conditioning and reference-anchored attention alignment to achieve better temporal coherence and localized edits.
StreamEdit enables high-quality training-free video editing by adapting streaming video generation models with dual-branch fast sampling, self-attention bridge, cross-attention grounding, source-oriented guidance, and visual prompting, outperforming prior methods in few-step regimes.
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.
A new keyframe selection framework combines structural, tracking, and semantic criteria to select reliable anchor frames for diffusion-based video editing under occlusion.
Bernini is a framework that uses an MLLM planner to output semantic representations for a DiT renderer to generate or edit videos, reporting SOTA benchmark performance.
citing papers explorer
-
StreamingEffect: Real-Time Human-Centric Video Effect Generation
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
-
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.
-
LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing
A three-stage distillation plus AR mask cache converts a bidirectional DiT editor into a real-time causal streaming editor that preserves non-edited regions at 12.66 FPS.
-
SteerVTE: Seamless Video Text Editing with Style and Glyph Control
SteerVTE adds lightweight style and dual-granularity glyph adapters to a frozen video diffusion model, introduces a glyph-aware loss and progressive training, and releases a 1M synthetic dataset to enable accurate video text editing.
-
Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing
RVEDiT improves DiT-based video editing by granularity-routed token conditioning and reference-anchored attention alignment to achieve better temporal coherence and localized edits.
-
StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation
StreamEdit enables high-quality training-free video editing by adapting streaming video generation models with dual-branch fast sampling, self-attention bridge, cross-attention grounding, source-oriented guidance, and visual prompting, outperforming prior methods in few-step regimes.
-
LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
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.
-
Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing
A new keyframe selection framework combines structural, tracking, and semantic criteria to select reliable anchor frames for diffusion-based video editing under occlusion.
-
Bernini: Latent Semantic Planning for Video Diffusion
Bernini is a framework that uses an MLLM planner to output semantic representations for a DiT renderer to generate or edit videos, reporting SOTA benchmark performance.