Beyond Inpainting: Unleash 3D Understanding for Stable Camera-Controlled Video Generation

arXiv:2601.10214 · cs.CV, cs.GR · Submitted 2026-01-15 · Read on arXiv

cs.CV, cs.GR

Submitted: 2026-01-15

Updated: 2026-09-27

Project page: https://eleanor6725.github.io/DepthDirector

Terminology

• Diffusion Model — 18× in this paper · explained in 8 episodes
• Consistency — 13× in this paper · explained in 3 episodes
• Diffusion Models — 13× in this paper · explained in 6 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Transformer — 11× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Ablation study — 6× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Flow Matching — 3× in this paper · explained in 8 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Fidelity — 2× in this paper · explained in 2 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Point Clouds — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• D Variational Auto-Encoder — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Reference Similarity — 1× in this paper
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Variational Bayes — 1× in this paper · explained in 2 episodes

Sources

• AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers
• VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
• SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
• GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
• Wan: Open and Advanced Large-Scale Video Generative Models
• Dens3R: A Foundation Model for 3D Geometry Prediction
• Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
• CameraCtrl: Enabling Camera Control for Text-to-Video Generation
• Training-free Camera Control for Video Generation
• LoRA: Low-Rank Adaptation of Large Language Models
• ViPE: Video Pose Engine for 3D Geometric Perception
• FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis
• MapAnything: Universal Feed-Forward Metric 3D Reconstruction
• Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control
• MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos
• MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second
• Depth Anything 3: Recovering the Visual Space from Any Views

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