# Memory-Guided B-Roll Generation from User Video Collections

arXiv: https://arxiv.org/abs/2610.01884 · HTML: https://mlsanity.com/paper/2610.01884/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 29 of 29)

- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [Re-Imagen: Retrieval-Augmented Text-to-Image Generator](https://mlsanity.com/paper/2209.14491/) (2022)
- [DreamVideo: Composing Your Dream Videos with Customized Subject and Motion](https://mlsanity.com/paper/2312.04433/) (2023)
- [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://mlsanity.com/paper/2411.17440/) (2024)
- [VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning](https://mlsanity.com/paper/2309.15091/) (2023)
- [VideoBooth: Diffusion-based Video Generation with Image Prompts](https://mlsanity.com/paper/2312.00777/) (2023)
- [Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation](https://mlsanity.com/paper/2307.06940/) (2023)
- [MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence](https://mlsanity.com/paper/2407.16655/) (2024)
- [VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos](https://mlsanity.com/paper/2502.01549/) (2025)
- [TaleCrafter: Interactive Story Visualization with Multiple Characters](https://mlsanity.com/paper/2305.18247/) (2023)
- [VideoRAG: Retrieval-Augmented Generation over Video Corpus](https://mlsanity.com/paper/2501.05874/) (2025)
- [StoryMem: Multi-shot Long Video Storytelling with Memory](https://mlsanity.com/paper/2512.19539/) (2025)
- [AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort](https://mlsanity.com/paper/2311.11243/) (2023)
- [EchoShot: Multi-Shot Portrait Video Generation](https://mlsanity.com/paper/2506.15838/) (2025)
- [VideoMemory: Toward Consistent Video Generation via Memory Integration](https://mlsanity.com/paper/2601.03655/) (2026)
- [ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation](https://mlsanity.com/paper/2502.09411/) (2025)
- [B-Script: Transcript-based B-roll Video Editing with Recommendations](https://mlsanity.com/paper/1902.11216/) (2019)
- [EditDuet: A Multi-Agent System for Video Non-Linear Editing](https://mlsanity.com/paper/2509.10761/) (2025)
- [Transcript to Video: Efficient Clip Sequencing from Texts](https://mlsanity.com/paper/2107.11851/) (2021)
- [Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection](https://mlsanity.com/paper/2409.19624/) (2024)
- [RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation](https://mlsanity.com/paper/2505.01657/) (2025)
- [DreamRunner: Fine-Grained Compositional Story-to-Video Generation with Retrieval-Augmented Motion Adaptation](https://mlsanity.com/paper/2411.16657/) (2024)
- [IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generation](https://mlsanity.com/paper/2512.23519/) (2025)
- [RAGME: Retrieval Augmented Video Generation for Enhanced Motion Realism](https://mlsanity.com/paper/2504.06672/) (2025)
- [AutoCut: End-to-end advertisement video editing based on multimodal discretization and controllable generation](https://mlsanity.com/paper/2603.28366/) (2026)
- [CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboarding](https://mlsanity.com/paper/2604.13452/) (2026)
- [Lights, Camera, Consistency: A Multistage Pipeline for Character-Stable AI Video Stories](https://mlsanity.com/paper/2512.16954/) (2025)
- [Vidmento: Creating Video Stories Through Context-Aware Expansion With Generative Video](https://mlsanity.com/paper/2601.22013/) (2026)
- [DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior](https://mlsanity.com/paper/2604.17195/) (2026)

## Abstract (arXiv)

We introduce an approach for collection-grounded B-roll sequence generation. Given a user's video collection, a directive given in natural language, and a target duration, the goal is to produce a multi-shot sequence that complements the user's primary footage (A-roll) while preserving the collection's characters, settings, objects, and style. This task is challenging as one must choose the visual evidence from hours of captured footage that should guide the generation of each shot in the sequence. We address this challenge with MemComposer, a three-stage system that turns raw footage into a structured memory with visual references (characters, settings, objects, and style) and uses it to plan, retrieve, and generate grounded B-roll sequences. First, in a one-time offline stage, MemComposer constructs an entity-centric memory from raw video. Second, it uses the memory and user directive to plan a grounded sequence and retrieve conditioning frames for each shot. Third, it iteratively generates and critiques the sequence to enforce identity, setting, and sequence-level consistency. We evaluate MemComposer in a user preference study along two dimensions: prompt adherence and visual alignment to the user's collection. Against an ungrounded text-to-video planner, MemComposer wins 60.0% of prompt-adherence and 92.8% of visual-alignment comparisons, showing the grounding benefit of collection memory and reference retrieval. Against retrieval-only sequences assembled from captured footage, MemComposer wins 94.5% of prompt-adherence comparisons, showing the value of generating missing shots, while retrieval-only sequences are preferred for visual alignment in 58.2% of comparisons.