Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation

arXiv 2023 35.9 method

TLDR

Proposes VidRD, a framework using latent diffusion models to iteratively generate additional video frames for text-to-video generation with improved temporal consistency.

Reasoning

The paper presents a clear method for extending video frames using latent diffusion and includes quantitative and qualitative evaluations. However, the abstract lacks explicit discussion of limitations or comparisons to broader world model frameworks, and the connection to world modeling is indirect.

Read-first score

Read-first score 35.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 5.

Recency 8%

65.1

Uses a gentle age decay so recent papers surface without erasing older foundations. 2023

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=dataset,evaluation,experiment,result

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code,dataset,github

Topical relevance 42%

7.1

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Field roles

Candidate

Rank sensitivity

Stability: volatile; rank range: 90.

Keyword Scores

video world model

world model

generative world model

world dynamics prediction

world simulator

interactive world model

model-based reinforcement learning world model

Resources

Paper