Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control

CVPR 25 2025 71.3 method, benchmark, application

TLDR

GEM is a multimodal world model for controllable future frame prediction with ego-motion, object dynamics, and human pose control, using a large real-world dataset.

Reasoning

The paper presents a novel world model with fine-grained control and long-horizon generation, supported by a large multimodal dataset and a new controllability metric. However, reliance on pseudo-labels and lack of explicit comparison to baselines may limit validation of its generalizability.

Read-first score

Read-first score 71.3, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 53.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Methodology quality 25%
80

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

Topical relevance 42%
75.7

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

Reproducibility 25%
50

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

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 38.

Keyword Scores

world model
10
generative world model
9
video world model
9
world dynamics prediction
9
world simulator
8
interactive world model
7
model-based reinforcement learning world model
1

Deep Analysis

Innovations

  • Predicts future frames using reference frame, sparse features, human poses, and ego-trajectories for fine-grained control over object dynamics, ego-agent motion, and human poses
  • Generates paired RGB and depth outputs for richer spatial understanding
  • Introduces autoregressive noise schedules to enable stable long-horizon generations
  • New Control of Object Manipulation (COM) metric to assess controllability
  • Large-scale multimodal dataset of 4000+ hours across autonomous driving, egocentric human activities, and drone flights

Methodology

GEM is a multimodal world model that takes a reference frame, sparse features, human poses, and ego-trajectories as inputs to predict future frames. It generates paired RGB and depth outputs using autoregressive noise schedules for stable long-horizon generation. The model is trained on a dataset of 4000+ hours of multimodal data with pseudo-labels for depth, ego-trajectories, and human poses, and evaluated using a comprehensive framework including the COM metric.

Key Results

Experiments show GEM excels at generating diverse, controllable scenarios and maintains temporal consistency over long generations.

Tags