Cover Image

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Yanjun, Zhang, Zhengqiang, Wang, Pengfei, Liang, Xinyue, Ma, Zhiyuan, Zhang, Lei
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation
by: Liang, Xinyue, et al.
Published: (2025)

One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Image
by: Wang, Pengfei, et al.
Published: (2026)

Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation
by: Zhu, Tianrui, et al.
Published: (2025)

Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation
by: Li, Ruibin, et al.
Published: (2026)

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval
by: Yu, Jiwen, et al.
Published: (2025)

Photo3D: Advancing Photorealistic 3D Generation through Structure-Aligned Detail Enhancement
by: Liang, Xinyue, et al.
Published: (2025)

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory
by: Yang, Zhenhao, et al.
Published: (2026)

GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation
by: Zhang, Zhengqiang, et al.
Published: (2025)

SSL: A Self-similarity Loss for Improving Generative Image Super-resolution
by: Chen, Du, et al.
Published: (2024)

TMP: Temporal Motion Propagation for Online Video Super-Resolution
by: Zhang, Zhengqiang, et al.
Published: (2023)

FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling
by: Zhang, Zhengqiang, et al.
Published: (2024)

One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
by: Sun, Yujing, et al.
Published: (2025)

SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA
by: Zheng, Xinyi, et al.
Published: (2026)

MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
by: Ji, Sihui, et al.
Published: (2025)

Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation
by: Han, Yizhao, et al.
Published: (2026)

AutoScape: Geometry-Consistent Long-Horizon Scene Generation
by: Chen, Jiacheng, et al.
Published: (2025)

Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation
by: Chen, Yuheng, et al.
Published: (2026)

VideoMemory: Toward Consistent Video Generation via Memory Integration
by: Zhou, Jinsong, et al.
Published: (2026)

Pack and Force Your Memory: Long-form and Consistent Video Generation
by: Wu, Xiaofei, et al.
Published: (2025)

Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding
by: Li, Ruihuang, et al.
Published: (2024)

Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion
by: Xiao, Chaodong, et al.
Published: (2024)

AnimateAnything: Consistent and Controllable Animation for Video Generation
by: Lei, Guojun, et al.
Published: (2024)

Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation
by: Zhao, Zengqun, et al.
Published: (2026)

AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
by: Wang, Zun, et al.
Published: (2026)

ESCAPE: Episodic Spatial Memory and Adaptive Execution Policy for Long-Horizon Mobile Manipulation
by: Qian, Jingjing, et al.
Published: (2026)

RELIC: Interactive Video World Model with Long-Horizon Memory
by: Hong, Yicong, et al.
Published: (2025)

PanFlow: Decoupled Motion Control for Panoramic Video Generation
by: Zhang, Cheng, et al.
Published: (2025)

BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers
by: Xiao, Chaodong, et al.
Published: (2026)

Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution
by: Sun, Lingchen, et al.
Published: (2023)

Fast Multi-view Consistent 3D Editing with Video Priors
by: Chen, Liyi, et al.
Published: (2025)

Omni-3DEdit: Generalized Versatile 3D Editing in One-Pass
by: Liyi, Chen, et al.
Published: (2026)

InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPO
by: Fang, Xueji, et al.
Published: (2025)

SyncNoise: Geometrically Consistent Noise Prediction for Text-based 3D Scene Editing
by: Li, Ruihuang, et al.
Published: (2024)

Detecting AI-Generated Video via Frame Consistency
by: Ma, Long, et al.
Published: (2024)

VAST 1.0: A Unified Framework for Controllable and Consistent Video Generation
by: Zhang, Chi, et al.
Published: (2024)

Consistent Human Image and Video Generation with Spatially Conditioned Diffusion
by: Cao, Mingdeng, et al.
Published: (2024)

Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data
by: Ma, Zhiyuan, et al.
Published: (2025)

Video World Models with Long-term Spatial Memory
by: Wu, Tong, et al.
Published: (2025)

Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation
by: Zhang, Haojie, et al.
Published: (2024)

SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation
by: Dou, Weijia, et al.
Published: (2026)