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.
Fastvmt: Eliminat- ing redundancy in video motion transfer
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 7years
2026 7roles
background 1polarities
background 1representative citing papers
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
GeoEdit introduces a Lift-Manipulate-Render-Denoise pipeline with dual-branch denoising and variance-homogeneous injection for 3D-consistent object editing in single photos.
Meta-CoT uses two-level decomposition of editing operations into meta-tasks and a CoT consistency reward to improve granularity and generalization, reporting 15.8% gains across 21 tasks.
Disco-LoRA proposes disentangling content-style and content-motion via dual-LoRA with statistical regularization to enable multi-concept video customization.
EasyVFX decouples VFX generation via frequency-aware Mixture-of-Experts and test-time training to achieve realistic effects with limited resources.
Empirical study shows reward model ensembles mitigate biases like brightness and composition in preference data for image inpainting, yielding better performance than prior methods without architecture changes.
citing papers explorer
-
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.
-
ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
-
GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising
GeoEdit introduces a Lift-Manipulate-Render-Denoise pipeline with dual-branch denoising and variance-homogeneous injection for 3D-consistent object editing in single photos.
-
Meta-CoT: Enhancing Granularity and Generalization in Image Editing
Meta-CoT uses two-level decomposition of editing operations into meta-tasks and a CoT consistency reward to improve granularity and generalization, reporting 15.8% gains across 21 tasks.
-
Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization
Disco-LoRA proposes disentangling content-style and content-motion via dual-LoRA with statistical regularization to enable multi-concept video customization.
-
EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation
EasyVFX decouples VFX generation via frequency-aware Mixture-of-Experts and test-time training to achieve realistic effects with limited resources.
-
Follow-Your-Preference++: Rethinking Preference Alignment for Image Inpainting
Empirical study shows reward model ensembles mitigate biases like brightness and composition in preference data for image inpainting, yielding better performance than prior methods without architecture changes.