VideoMemory: Toward Consistent Video Generation via Memory Integration

• URL: http://arxiv.org/abs/2601.03655v1
• Date: Wed, 07 Jan 2026 07:10:32 GMT
• Title: VideoMemory: Toward Consistent Video Generation via Memory Integration
• Authors: Jinsong Zhou, Yihua Du, Xinli Xu, Luozhou Wang, Zijie Zhuang, Yehang Zhang, Shuaibo Li, Xiaojun Hu, Bolan Su, Ying-cong Chen,
• Abstract summary: VideoMemory integrates narrative planning with visual generation through a Dynamic Memory Bank.<n>The Dynamic Memory Bank stores explicit visual and semantic descriptors for characters, props, and backgrounds.<n>This retrieval-update mechanism enables consistent portrayal of entities across distant shots and supports coherent long-form generation.
• Score: 28.605816634949814
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Maintaining consistent characters, props, and environments across multiple shots is a central challenge in narrative video generation. Existing models can produce high-quality short clips but often fail to preserve entity identity and appearance when scenes change or when entities reappear after long temporal gaps. We present VideoMemory, an entity-centric framework that integrates narrative planning with visual generation through a Dynamic Memory Bank. Given a structured script, a multi-agent system decomposes the narrative into shots, retrieves entity representations from memory, and synthesizes keyframes and videos conditioned on these retrieved states. The Dynamic Memory Bank stores explicit visual and semantic descriptors for characters, props, and backgrounds, and is updated after each shot to reflect story-driven changes while preserving identity. This retrieval-update mechanism enables consistent portrayal of entities across distant shots and supports coherent long-form generation. To evaluate this setting, we construct a 54-case multi-shot consistency benchmark covering character-, prop-, and background-persistent scenarios. Extensive experiments show that VideoMemory achieves strong entity-level coherence and high perceptual quality across diverse narrative sequences.

Related papers

• CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation [9.91271343855315]
  CoAgent is a framework for coherent video generation that formulates the process as a plan-synthesize-verify pipeline.<n>A Storyboard Planner decomposes the input into structured shot-level plans with explicit entities, spatial relations, and temporal cues.<n>A Global Context Manager maintains entity-level memory to preserve appearance and identity consistency across shots.<n>A pacing-aware editor refines temporal rhythm and transitions to match the desired narrative flow.
  arXiv  Detail & Related papers  (2025-12-27T09:38:34Z)
• StoryMem: Multi-shot Long Video Storytelling with Memory [32.97816766878247]
  We propose StoryMem, a paradigm that reformulates long-form video storytelling as iterative shot synthesis conditioned on explicit visual memory.<n>The proposed framework naturally accommodates smooth shot transitions and customized story generation applications.
  arXiv  Detail & Related papers  (2025-12-22T16:23:24Z)
• STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative [55.05324155854762]
  We introduce a SToryboard-Anchored GEneration workflow to reformulate the STAGE-based video generation task.<n>Instead of using sparses, we propose STEP2 to predict a structural storyboard composed of start-end frame pairs for each shot.<n>We also contribute the large-scale ConStoryBoard dataset, including high-quality movie clips with fine-grained narratives for story progression, cinematic attributes, and human preferences.
  arXiv  Detail & Related papers  (2025-12-13T15:57:29Z)
• FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion [46.67733869872552]
  textbfFilmWeaver is a framework designed to generate consistent, multi-shot videos of arbitrary length.<n>Our key insight is to decouple the problem into inter-shot consistency and intra-shot coherence.<n>Our method surpasses existing approaches on metrics for both consistency and aesthetic quality.
  arXiv  Detail & Related papers  (2025-12-12T04:34:53Z)
• AlcheMinT: Fine-grained Temporal Control for Multi-Reference Consistent Video Generation [58.844504598618094]
  We propose AlcheMinT, a unified framework that introduces explicit timestamps conditioning for subject-driven video generation.<n>Our approach introduces a novel positional encoding mechanism that unlocks the encoding of temporal intervals, associated in our case with subject identities.<n>We incorporate subject-descriptive text tokens to strengthen binding between visual identity and video captions, mitigating ambiguity during generation.
  arXiv  Detail & Related papers  (2025-12-11T18:59:34Z)
• WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning [66.24870234484668]
  We introduce WorldMM, a novel multimodal memory agent that constructs and retrieves from multiple complementary memories.<n>WorldMM significantly outperforms existing baselines across five long video question-answering benchmarks.
  arXiv  Detail & Related papers  (2025-12-02T05:14:52Z)
• SceneRAG: Scene-level Retrieval-Augmented Generation for Video Understanding [6.980340270823506]
  We present SceneRAG, a framework to segment videos into narrative-consistent scenes.<n>For each scene, the framework fuses information from both visual and textual modalities to extract entity relations.<n>Experiments on the LongerVideos benchmark, featuring over 134 hours of diverse content, confirm that SceneRAG substantially outperforms prior baselines.
  arXiv  Detail & Related papers  (2025-06-09T10:00:54Z)
• VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention [76.3175166538482]
  VideoGen-of-Thought (VGoT) is a step-by-step framework that automates multi-shot video synthesis from a single sentence.<n>VGoT addresses three core challenges: Narrative fragmentation, visual inconsistency, and transition artifacts.<n>Combined in a training-free pipeline, VGoT surpasses strong baselines by 20.4% in within-shot face consistency and 17.4% in style consistency.
  arXiv  Detail & Related papers  (2024-12-03T08:33:50Z)
• Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection [27.412361280397057]
  We introduce Storynizor, a model capable of generating coherent stories with strong inter-frame character consistency. Key innovation of Storynizor lies in its key modules: ID-Synchronizer and ID-Injector. To facilitate the training of Storynizor, we have curated a novel dataset called StoryDB comprising 100, 000 images.
  arXiv  Detail & Related papers  (2024-09-29T09:15:51Z)
• TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation [97.96178992465511]
  We argue that generated videos should incorporate the emergence of new concepts and their relation transitions like in real-world videos as time progresses. To assess the Temporal Compositionality of video generation models, we propose TC-Bench, a benchmark of meticulously crafted text prompts, corresponding ground truth videos, and robust evaluation metrics.
  arXiv  Detail & Related papers  (2024-06-12T21:41:32Z)
• Make-A-Story: Visual Memory Conditioned Consistent Story Generation [57.691064030235985]
  We propose a novel autoregressive diffusion-based framework with a visual memory module that implicitly captures the actor and background context. Our method outperforms prior state-of-the-art in generating frames with high visual quality. Our experiments for story generation on the MUGEN, the PororoSV and the FlintstonesSV dataset show that our method not only outperforms prior state-of-the-art in generating frames with high visual quality, but also models appropriate correspondences between the characters and the background.
  arXiv  Detail & Related papers  (2022-11-23T21:38:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.