SUDS: Scalable Urban Dynamic Scenes

arXiv 2023 26.7 method

TLDR

SUDS scales neural radiance fields to dynamic large-scale urban scenes using factorized hash tables and unlabeled signals like optical flow, enabling reconstruction from 1.2M frames.

Reasoning

The paper introduces useful scalability innovations for dynamic NeRFs and demonstrates them on a large real-world dataset. However, the abstract mentions only qualitative initial results and lacks quantitative evaluations or comparisons, limiting evidence of effectiveness.

Read-first score

Read-first score 26.7, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 3.

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=metric,result

Reproducibility 25%

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

Topical relevance 42%

4.3

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: 51.

Keyword Scores

world model

generative world model

video world model

world simulator

interactive world model

world dynamics prediction

model-based reinforcement learning world model

Resources

Paper