- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper introduces OasisData-Engine and Oasis-World. The former is an automated Unreal Engine pipeline for synthesizing synchronized, action-annotated multi-agent videos. The resulting OasisData contains over 4,900 hours across 132 environments and more than 80 characters, covering configurations of one to ten agents. The latter is a Wan2.2-5B-based world model that uses per-agent action conditioning and cross-agent attention to jointly generate multiple viewpoints, training on the proposed dataset.
Critical strengths
- The biggest contribution is the dataset. Existing world model datasets are either egocentric navigation, or single character movement. OasisData provides practical resources in multi-agent world model area.
- The dataset covers satisfying amount of data, coveraging different characters and scenes. Meanwhile, the data engine is scalable, providing useful infrastructure for further data collection.
- Oasis-World offers a straightforward baseline and demonstrates benefits from cross-agent information exchange over independent single-agent generation.
Critical weaknesses
- Direct comparison with other multi-agent world model is preferable. Evaluation only compares against independent single-agent generation. MultiWorld[1] should be included for comparison.
- The consistency of the GPT-Image-2-generated input pairs is not established. Held-out UE scenarios with ground-truth geometry would provide more reliable spatial-consistency measurements.
- The dataset covers up to 10 agents, yet the evaluation only focus on 2. Scalability of agents number should be clarified.
[1] MultiWorld: Scalable Multi-Agent Multi-View Video World Models. Wu et al.
Questions for authors
Please see weakness.