4Director: Controlling Video World Models with Rigid 3D Geometry

arXiv:2610.02160 · cs.CV · Submitted 2026-10-01 · Read on arXiv

cs.CV

Submitted: 2026-10-01

Updated: 2026-10-01

Project page: https://stability-ai.github.io/4director

Terminology

• World Model — 23× in this paper · explained in 7 episodes
• Consistency — 12× in this paper · explained in 3 episodes
• Diffusion Model — 11× in this paper · explained in 8 episodes
• Computer Vision and Pattern Recognition — 10× in this paper
• Diffusion Models — 9× in this paper · explained in 6 episodes
• CVF International Conference on Computer Vision — 8× in this paper
• Transformer — 7× in this paper · explained in 2 episodes
• Adam — 6× in this paper · explained in 2 episodes
• Alignment — 6× in this paper · explained in 1 episode
• Core — 6× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• In European Conference on Computer Vision — 4× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• In International Conference on Learning Representations — 3× in this paper
• Actor — 2× in this paper · explained in 3 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• In International Conference on Machine Learning — 2× in this paper
• Ablation study — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Continual Learning — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Synthetic Data Generation — 1× in this paper · explained in 5 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes

Sources

• Cosmos World Foundation Model Platform for Physical AI
• Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
• VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
• SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
• Qwen3-VL Technical Report
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• Pseudo-Simulation for Autonomous Driving
• SAM 3: Segment Anything with Concepts
• DeepVerse: 4D Autoregressive Video Generation as a World Model
• Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
• Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
• LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models
• I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength
• I2VControl: Disentangled and Unified Video Motion Synthesis Control
• World Models
• Mastering Diverse Domains through World Models
• CameraCtrl: Enabling Camera Control for Text-to-Video Generation
• CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models
• Matrix-game 2.0: An open-source, real-time, and streaming interactive world model
• RELIC: Interactive Video World Model with Long-Horizon Memory

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models