CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation

arXiv 2024 23.3 method

TLDR

CamCo introduces camera pose control for image-to-video generation using Plücker coordinates and epipolar attention, improving 3D consistency and object motion on real-world videos.

Reasoning

The paper presents a clear method for camera-controllable video generation with strong technical contributions, including epipolar attention for 3D consistency and fine-tuning on real-world videos. However, it does not address world models or dynamics prediction, and the abstract provides limited discussion of limitations or broader generalization.

Read-first score

Read-first score 23.3, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 0.

Recency 8%

75.1

Uses a gentle age decay so recent papers surface without erasing older foundations. 2024

Reproducibility 25%

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

Methodology quality 25%

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

Topical relevance 42%

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: 58.

Keyword Scores

world model

world simulator

generative world model

interactive world model

video world model

world dynamics prediction

model-based reinforcement learning world model

Resources

Paper