SE-Mem: Semantic-Episodic Memory for Scene-Consistent Generative View Synthesis
cs.CV
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation
- Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
- CameraCtrl: Enabling Camera Control for Text-to-Video Generation
- Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
- Wan: Open and Advanced Large-Scale Video Generative Models
- Video World Models with Long-term Spatial Memory
- WorldMem: Long-term Consistent World Simulation with Memory
- CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
- ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
- Stereo Magnification: Learning View Synthesis using Multiplane Images
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs