# FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis

arXiv: https://arxiv.org/abs/2502.08244 · HTML: https://mlsanity.com/paper/2502.08244/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 41 of its 50 references that are in the map.
- First posted on arXiv 12 Feb 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 41)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [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)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [MotionCtrl: A Unified and Flexible Motion Controller for Video Generation](https://mlsanity.com/paper/2312.03641/) (2023)
- [CameraCtrl: Enabling Camera Control for Text-to-Video Generation](https://mlsanity.com/paper/2404.02101/) (2024)
- [Latent Video Diffusion Models for High-Fidelity Long Video Generation](https://mlsanity.com/paper/2211.13221/) (2022)
- [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](https://mlsanity.com/paper/2106.02634/) (2021)
- [DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory](https://mlsanity.com/paper/2308.08089/) (2023)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [Stereo Magnification: Learning View Synthesis using Multiplane Images](https://mlsanity.com/paper/1805.09817/) (2018)
- [Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling](https://mlsanity.com/paper/2401.15977/) (2024)
- [Thin-Plate Spline Motion Model for Image Animation](https://mlsanity.com/paper/2203.14367/) (2022)
- [Conditional Image-to-Video Generation with Latent Flow Diffusion Models](https://mlsanity.com/paper/2303.13744/) (2023)
- [Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion](https://mlsanity.com/paper/2402.03162/) (2024)
- [CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation](https://mlsanity.com/paper/2406.02509/) (2024)
- [VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control](https://mlsanity.com/paper/2407.12781/) (2024)
- [CamI2V: Camera-Controlled Image-to-Video Diffusion Model](https://mlsanity.com/paper/2410.15957/) (2024)

## Built on by (most cited first, 30 of 37)

- [Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation](https://mlsanity.com/paper/2509.19296/) (2025)
- [EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance](https://mlsanity.com/paper/2505.21876/) (2025)
- [WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories](https://mlsanity.com/paper/2603.02049/) (2026)
- [AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories](https://mlsanity.com/paper/2602.14941/) (2026)
- [Video-As-Prompt: Unified Semantic Control for Video Generation](https://mlsanity.com/paper/2510.20888/) (2025)
- [3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation](https://mlsanity.com/paper/2510.14945/) (2025)
- [DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation](https://mlsanity.com/paper/2511.23127/) (2025)
- [Lynx: Towards High-Fidelity Personalized Video Generation](https://mlsanity.com/paper/2509.15496/) (2025)
- [VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models](https://mlsanity.com/paper/2509.17985/) (2025)
- [3D Scene Understanding Through Local Random Access Sequence Modeling](https://mlsanity.com/paper/2504.03875/) (2025)
- [TeRA: Rethinking Text-guided Realistic 3D Avatar Generation](https://mlsanity.com/paper/2509.02466/) (2025)
- [Open-world Hand-Object Interaction Video Generation Based on Structure and Contact-aware Representation](https://mlsanity.com/paper/2512.01677/) (2025)
- [WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling](https://mlsanity.com/paper/2512.07821/) (2025)
- [LAMP: Language-Assisted Motion Planning for Controllable Video Generation](https://mlsanity.com/paper/2512.03619/) (2025)
- [VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification](https://mlsanity.com/paper/2512.09646/) (2025)
- [Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute](https://mlsanity.com/paper/2504.17816/) (2025)
- [CloseUpShot: Close-up Novel View Synthesis from Sparse-views via Point-conditioned Diffusion Model](https://mlsanity.com/paper/2511.13121/) (2025)
- [MoRight: Motion Control Done Right](https://mlsanity.com/paper/2604.07348/) (2026)
- [World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks](https://mlsanity.com/paper/2605.19957/) (2026)
- [Unified 3D Scene Understanding Through Physical World Modeling](https://mlsanity.com/paper/2605.24321/) (2026)
- [FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models](https://mlsanity.com/paper/2504.14535/) (2025)
- [OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance](https://mlsanity.com/paper/2603.18639/) (2026)
- [Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation](https://mlsanity.com/paper/2606.01900/) (2026)
- [Go-with-the-Track: Video Compositing and Motion Control with Point Tracking](https://mlsanity.com/paper/2606.20891/) (2026)
- [From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting](https://mlsanity.com/paper/2607.14976/) (2026)
- [GeoDiffMM: Geometry-Guided Conditional Diffusion for Motion Magnification](https://mlsanity.com/paper/2512.08325/) (2025)
- [Beyond Inpainting: Unleash 3D Understanding for Precise Camera-Controlled Video Generation](https://mlsanity.com/paper/2601.10214/) (2026)
- [Video2LoRA: Unified Semantic-Controlled Video Generation via Per-Reference-Video LoRA](https://mlsanity.com/paper/2603.08210/) (2026)
- [DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data](https://mlsanity.com/paper/2604.01666/) (2026)
- [OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control](https://mlsanity.com/paper/2604.06010/) (2026)

## Abstract (arXiv)

We present FloVD, a novel video diffusion model for camera-controllable video generation. FloVD leverages optical flow to represent the motions of the camera and moving objects. This approach offers two key benefits. Since optical flow can be directly estimated from videos, our approach allows for the use of arbitrary training videos without ground-truth camera parameters. Moreover, as background optical flow encodes 3D correlation across different viewpoints, our method enables detailed camera control by leveraging the background motion. To synthesize natural object motion while supporting detailed camera control, our framework adopts a two-stage video synthesis pipeline consisting of optical flow generation and flow-conditioned video synthesis. Extensive experiments demonstrate the superiority of our method over previous approaches in terms of accurate camera control and natural object motion synthesis.