# MeRoPE: Metric Rotary Position Embedding for Camera-Controlled Video Generation

arXiv: https://arxiv.org/abs/2609.01252 · HTML: https://mlsanity.com/paper/2609.01252/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 26 of 26)

- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [MotionCtrl: A Unified and Flexible Motion Controller for Video Generation](https://mlsanity.com/paper/2312.03641/) (2023)
- [ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis](https://mlsanity.com/paper/2409.02048/) (2024)
- [GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control](https://mlsanity.com/paper/2503.03751/) (2025)
- [ReCamMaster: Camera-Controlled Generative Rendering from A Single Video](https://mlsanity.com/paper/2503.11647/) (2025)
- [CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation](https://mlsanity.com/paper/2406.02509/) (2024)
- [TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models](https://mlsanity.com/paper/2503.05638/) (2025)
- [Cameras as Relative Positional Encoding](https://mlsanity.com/paper/2507.10496/) (2025)
- [EscherNet: A Generative Model for Scalable View Synthesis](https://mlsanity.com/paper/2402.03908/) (2024)
- [GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers](https://mlsanity.com/paper/2310.10375/) (2023)
- [Lyra 2.0: Explorable Generative 3D Worlds](https://mlsanity.com/paper/2604.13036/) (2026)
- [Unified Camera Positional Encoding for Controlled Video Generation](https://mlsanity.com/paper/2512.07237/) (2025)
- [BulletTime: Decoupled Control of Time and Camera Pose for Video Generation](https://mlsanity.com/paper/2512.05076/) (2025)
- [RayRoPE: Projective Ray Positional Encoding for Multi-view Attention](https://mlsanity.com/paper/2601.15275/) (2026)
- [ReRoPE: Repurposing RoPE for Relative Camera Control](https://mlsanity.com/paper/2602.08068/) (2026)
- [Geometry-Aware Rotary Position Embedding for Consistent Video World Model](https://mlsanity.com/paper/2602.07854/) (2026)
- [Grounding World Simulation Models in a Real-World Metropolis](https://mlsanity.com/paper/2603.15583/) (2026)
- [World Engine: Towards the Era of Post-Training for Autonomous Driving](https://mlsanity.com/paper/2606.19836/) (2026)
- [URoPE: Universal Relative Position Embedding across Geometric Spaces](https://mlsanity.com/paper/2604.18747/) (2026)
- [RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space](https://mlsanity.com/paper/2602.20685/) (2026)
- [CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation](https://mlsanity.com/paper/2605.12938/) (2026)
- [Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation](https://mlsanity.com/paper/2603.12864/) (2026)
- [CityRAG: Stepping Into a City via Spatially-Grounded Video Generation](https://mlsanity.com/paper/2604.19741/) (2026)

## Built on by (most cited first, 1 of 1)

- [LOCI: Spatial Linear Memory for Streaming World Models](https://mlsanity.com/paper/2609.40222/) (2026)

## Abstract (arXiv)

In camera-controlled video generation, geometry-aware positional encodings condition tokens on camera extrinsics and per-token viewing rays. Existing schemes, however, have a scale-dependent failure mode on real-world metric camera trajectories: homogeneous projective encodings cause attention logits and feature norms to grow unbounded with physical translation baselines. We propose MeRoPE (Metric Rotary Position Embedding), a norm-preserving relative camera encoding for attention. MeRoPE encodes relative orientations between calibrated viewing rays with orthogonal rotation blocks, maps raw metric displacements into multi-frequency rotary phases, and adds a disparity-anchored correspondence prior along the epipolar arc. This design strictly preserves feature norms, bounds pre-softmax attention logits regardless of the physical translation scale, and maintains exact invariance to global rigid coordinate changes. Across nuScenes and PanShot, which cover large-baseline trajectories and diverse camera optics, respectively, MeRoPE achieves stronger camera control than prior encodings, with the best consistency between generated camera motion and conditioning poses in both rotation and translation. Code will be made publicly available.