NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

arXiv 26.1 2026 51.7 method, system

TLDR

NeoVerse is a scalable 4D world model from monocular videos, enabling reconstruction, novel-trajectory generation, and downstream tasks.

Reasoning

The paper proposes a novel pipeline that overcomes scalability issues in 4D world modeling by using pose-free feed-forward reconstruction and online degradation simulation. Strengths include state-of-the-art performance on benchmarks and generalization to diverse domains; weaknesses are not explicitly stated in the abstract, but the reliance on monocular videos may limit temporal consistency.

Read-first score

Read-first score 51.7, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 36.

Recency 8%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Topical relevance 42%

51.4

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

Methodology quality 25%

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

Reproducibility 25%

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

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 464.

Keyword Scores

world model

video world model

generative world model

world simulator

world dynamics prediction

interactive world model

model-based reinforcement learning world model

Deep Analysis

Innovations

Pose-free feed-forward 4D reconstruction
Online monocular degradation pattern simulation
Scalable to diverse in-the-wild monocular videos without expensive multi-view data or cumbersome pre-processing
Versatility and generalization to various domains for 4D reconstruction, novel-trajectory video generation, and downstream applications

Methodology

NeoVerse is a 4D world model that uses pose-free feed-forward 4D reconstruction and online monocular degradation pattern simulation to process in-the-wild monocular videos without requiring expensive multi-view data or cumbersome pre-processing. It is evaluated on standard reconstruction and generation benchmarks.

Key Results

NeoVerse achieves state-of-the-art performance in standard reconstruction and generation benchmarks.

Resources

Paper Project