LangDriveCTRL decomposes driving videos into 3D scene graphs and uses an agentic pipeline with specialized multi-modal agents to perform language-controlled object and behavior edits, achieving nearly 2x higher instruction alignment than prior state-of-the-art methods.
Five: A fine-grained video editing benchmark for evaluating emerging diffusion and rectified flow models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
fields
cs.CV 6verdicts
UNVERDICTED 6representative 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.
StreamGVE enables high-quality training-free video editing by converting the task to noise-to-data streaming generation with dual-branch fast sampling, self-attention bridges, cross-attention grounding, source-oriented guidance, and visual prompting.
VEFX-Bench releases a large human-labeled video editing dataset, a multi-dimensional reward model, and a standardized benchmark that better matches human judgments than generic evaluators.
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.
Omni is a multimodal model whose native training on diverse data types enables context unrolling, allowing explicit reasoning across modalities to better approximate shared knowledge and improve downstream performance.
citing papers explorer
-
LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents
LangDriveCTRL decomposes driving videos into 3D scene graphs and uses an agentic pipeline with specialized multi-modal agents to perform language-controlled object and behavior edits, achieving nearly 2x higher instruction alignment than prior state-of-the-art methods.
-
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.
-
StreamGVE: Training-Free Video Editing via Few-Step Streaming Video Generation
StreamGVE enables high-quality training-free video editing by converting the task to noise-to-data streaming generation with dual-branch fast sampling, self-attention bridges, cross-attention grounding, source-oriented guidance, and visual prompting.
-
VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects
VEFX-Bench releases a large human-labeled video editing dataset, a multi-dimensional reward model, and a standardized benchmark that better matches human judgments than generic evaluators.
-
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.
-
Context Unrolling in Omni Models
Omni is a multimodal model whose native training on diverse data types enables context unrolling, allowing explicit reasoning across modalities to better approximate shared knowledge and improve downstream performance.