# PEEKABOO: Interactive Video Generation via Masked-Diffusion

arXiv: https://arxiv.org/abs/2312.07509 · HTML: https://mlsanity.com/paper/2312.07509/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 30 of its 40 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

## Builds on (most cited first, 30 of 30)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing](https://mlsanity.com/paper/2304.08465/) (2023)
- [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://mlsanity.com/paper/2303.13439/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [Structure and Content-Guided Video Synthesis with Diffusion Models](https://mlsanity.com/paper/2302.03011/) (2023)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [MagicVideo: Efficient Video Generation With Latent Diffusion Models](https://mlsanity.com/paper/2211.11018/) (2022)
- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023)
- [Diffusion Self-Guidance for Controllable Image Generation](https://mlsanity.com/paper/2306.00986/) (2023)
- [Generalized Decoding for Pixel, Image, and Language](https://mlsanity.com/paper/2212.11270/) (2022)
- [LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models](https://mlsanity.com/paper/2305.13655/) (2023)
- [Grounded Text-to-Image Synthesis with Attention Refocusing](https://mlsanity.com/paper/2306.05427/) (2023)
- [VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning](https://mlsanity.com/paper/2309.15091/) (2023)
- [LaSOT: A High-quality Large-scale Single Object Tracking Benchmark](https://mlsanity.com/paper/2009.03465/) (2020)
- [Motion-Conditioned Diffusion Model for Controllable Video Synthesis](https://mlsanity.com/paper/2304.14404/) (2023)
- [LLM-grounded Video Diffusion Models](https://mlsanity.com/paper/2309.17444/) (2023)
- [A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis](https://mlsanity.com/paper/2306.14544/) (2023)
- [Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator](https://mlsanity.com/paper/2309.14494/) (2023)
- [On the effectiveness of task granularity for transfer learning](https://mlsanity.com/paper/1804.09235/) (2018)

## Built on by (most cited first, 30 of 76)

- [Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control](https://mlsanity.com/paper/2501.03847/) (2025)
- [Motion Prompting: Controlling Video Generation with Motion Trajectories](https://mlsanity.com/paper/2412.02700/) (2024)
- [Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion](https://mlsanity.com/paper/2402.03162/) (2024)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers](https://mlsanity.com/paper/2411.18673/) (2024)
- [CamI2V: Camera-Controlled Image-to-Video Diffusion Model](https://mlsanity.com/paper/2410.15957/) (2024)
- [Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise](https://mlsanity.com/paper/2501.08331/) (2025)
- [Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond](https://mlsanity.com/paper/2405.03520/) (2024)
- [Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control](https://mlsanity.com/paper/2503.14492/) (2025)
- [Learning Temporally Consistent Video Depth from Video Diffusion Priors](https://mlsanity.com/paper/2406.01493/) (2024)
- [Controllable Video Generation: A Survey](https://mlsanity.com/paper/2507.16869/) (2025)
- [MotionBooth: Motion-Aware Customized Text-to-Video Generation](https://mlsanity.com/paper/2406.17758/) (2024)
- [TrailBlazer: Trajectory Control for Diffusion-Based Video Generation](https://mlsanity.com/paper/2401.00896/) (2023)
- [ReVideo: Remake a Video with Motion and Content Control](https://mlsanity.com/paper/2405.13865/) (2024)
- [SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation](https://mlsanity.com/paper/2411.04989/) (2024)
- [MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance](https://mlsanity.com/paper/2503.16421/) (2025)
- [RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control](https://mlsanity.com/paper/2502.10059/) (2025)
- [FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models](https://mlsanity.com/paper/2406.16863/) (2024)
- [Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance](https://mlsanity.com/paper/2512.08765/) (2025)
- [DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control](https://mlsanity.com/paper/2410.13830/) (2024)
- [ATI: Any Trajectory Instruction for Controllable Video Generation](https://mlsanity.com/paper/2505.22944/) (2025)
- [AnimateAnything: Consistent and Controllable Animation for Video Generation](https://mlsanity.com/paper/2411.10836/) (2024)
- [MotionPro: A Precise Motion Controller for Image-to-Video Generation](https://mlsanity.com/paper/2505.20287/) (2025)
- [VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation](https://mlsanity.com/paper/2502.07531/) (2025)
- [I2VControl: Disentangled and Unified Video Motion Synthesis Control](https://mlsanity.com/paper/2411.17765/) (2024)
- [Compositional 3D-aware Video Generation with LLM Director](https://mlsanity.com/paper/2409.00558/) (2024)
- [ObjCtrl-2.5D: Training-free Object Control with Camera Poses](https://mlsanity.com/paper/2412.07721/) (2024)
- [Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation](https://mlsanity.com/paper/2501.01425/) (2025)
- [Simulating the Visual World with Artificial Intelligence: A Roadmap](https://mlsanity.com/paper/2511.08585/) (2025)
- [Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising](https://mlsanity.com/paper/2511.08633/) (2025)

## Abstract (arXiv)

Modern video generation models like Sora have achieved remarkable success in producing high-quality videos. However, a significant limitation is their inability to offer interactive control to users, a feature that promises to open up unprecedented applications and creativity. In this work, we introduce the first solution to equip diffusion-based video generation models with spatio-temporal control. We present Peekaboo, a novel masked attention module, which seamlessly integrates with current video generation models offering control without the need for additional training or inference overhead. To facilitate future research, we also introduce a comprehensive benchmark for interactive video generation. This benchmark offers a standardized framework for the community to assess the efficacy of emerging interactive video generation models. Our extensive qualitative and quantitative assessments reveal that Peekaboo achieves up to a 3.8x improvement in mIoU over baseline models, all while maintaining the same latency. Code and benchmark are available on the webpage.