DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles

arXiv 2023 33.3 method

TLDR

Proposes DDLP, an object-centric video prediction method using deep latent particles, achieving state-of-the-art results and enabling what-if generation and diffusion-based video generation.

Reasoning

The paper presents a novel representation and achieves strong empirical results on video prediction benchmarks, with interpretability and generative capabilities as key strengths. However, it does not explicitly frame itself as a world model or address interactive or RL settings, limiting relevance to those keywords.

Read-first score

Read-first score 33.3, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 9.

Recency 8%

65.1

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

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

Methodology quality 25%

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

Topical relevance 42%

12.9

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: 50.

Keyword Scores

video world model

world dynamics prediction

world model

generative world model

world simulator

interactive world model

model-based reinforcement learning world model

Resources

Paper