# CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization

arXiv: https://arxiv.org/abs/2512.19020 · HTML: https://mlsanity.com/paper/2512.19020/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 22 Dec 2025.

## Builds on (most cited first, 25 of 25)

- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [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)
- [ControlVideo: Training-free Controllable Text-to-Video Generation](https://mlsanity.com/paper/2305.13077/) (2023)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [ReCamMaster: Camera-Controlled Generative Rendering from A Single Video](https://mlsanity.com/paper/2503.11647/) (2025)
- [Stable Virtual Camera: Generative View Synthesis with Diffusion Models](https://mlsanity.com/paper/2503.14489/) (2025)
- [MotionDirector: Motion Customization of Text-to-Video Diffusion Models](https://mlsanity.com/paper/2310.08465/) (2023)
- [ViPE: Video Pose Engine for 3D Geometric Perception](https://mlsanity.com/paper/2508.10934/) (2025)
- [AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers](https://mlsanity.com/paper/2411.18673/) (2024)
- [Training-free Camera Control for Video Generation](https://mlsanity.com/paper/2406.10126/) (2024)
- [Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding](https://mlsanity.com/paper/2501.07888/) (2025)
- [Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation](https://mlsanity.com/paper/2504.14899/) (2025)
- [GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping](https://mlsanity.com/paper/2405.17251/) (2024)
- [MultiDiff: Consistent Novel View Synthesis from a Single Image](https://mlsanity.com/paper/2406.18524/) (2024)
- [Towards Understanding Camera Motions in Any Video](https://mlsanity.com/paper/2504.15376/) (2025)
- [FullDiT: Multi-Task Video Generative Foundation Model with Full Attention](https://mlsanity.com/paper/2503.19907/) (2025)
- [EX-4D: EXtreme Viewpoint 4D Video Synthesis via Depth Watertight Mesh](https://mlsanity.com/paper/2506.05554/) (2025)
- [CamCtrl3D: Single-Image Scene Exploration with Precise 3D Camera Control](https://mlsanity.com/paper/2501.06006/) (2025)
- [EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance](https://mlsanity.com/paper/2505.21876/) (2025)
- [Latent-Reframe: Enabling Camera Control for Video Diffusion Model without Training](https://mlsanity.com/paper/2412.06029/) (2024)

## Built on by (most cited first, 5 of 5)

- [MV-S2V: Multi-View Subject-Consistent Video Generation](https://mlsanity.com/paper/2601.17756/) (2026)
- [ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning](https://mlsanity.com/paper/2512.22854/) (2025)
- [WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling](https://mlsanity.com/paper/2607.03461/) (2026)
- [Honeycomb: Constant-Size Scene Memory Representation for Video World Models](https://mlsanity.com/paper/2609.37690/) (2026)
- [Harnessing LLMs as Agents: What Does It Cost?](https://mlsanity.com/paper/2610.02488/) (2026)

## Abstract (arXiv)

Achieving precise camera control in video generation remains challenging, as existing methods often rely on camera pose annotations that are difficult to scale to large and dynamic datasets and are frequently inconsistent with depth estimation, leading to train-test discrepancies. We introduce CETCAM, a camera-controllable video generation framework that eliminates the need for camera annotations through a consistent and extensible tokenization scheme. CETCAM leverages recent advances in geometry foundation models, such as VGGT, to estimate depth and camera parameters and converts them into unified, geometry-aware tokens. These tokens are seamlessly integrated into a pretrained video diffusion backbone via lightweight context blocks. Trained in two progressive stages, CETCAM first learns robust camera controllability from diverse raw video data and then refines fine-grained visual quality using curated high-fidelity datasets. Extensive experiments across multiple benchmarks demonstrate state-of-the-art geometric consistency, temporal stability, and visual realism. Moreover, CETCAM exhibits strong adaptability to additional control modalities, including inpainting and layout control, highlighting its flexibility beyond camera control. The project page is available at https://sjtuytc.github.io/CETCam_project_page.github.io/.