ReCap: Lightweight Referential Grounding for Coherent Story Visualization

• URL: http://arxiv.org/abs/2604.18575v1
• Date: Mon, 20 Apr 2026 17:57:50 GMT
• Title: ReCap: Lightweight Referential Grounding for Coherent Story Visualization
• Abstract summary: ReCap is a lightweight consistency framework that improves character stability and visual fidelity without modifying the base diffusion backbone.<n>ReCap's CORE (COnditional frame REferencing) module treats anaphors, in our case pronouns, as visual anchors, activating only when characters are referred to by a pronoun and conditioning on the preceding frame to propagate visual identity.<n>We extend story visualization to human-centric narratives derived from real films, demonstrating the capability of ReCap beyond stylized cartoon domains.
• Score: 11.022891519635834
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Story Visualization aims to generate a sequence of images that faithfully depicts a textual narrative that preserve character identity, spatial configuration, and stylistic coherence as the narratives unfold. Maintaining such cross-frame consistency has traditionally relied on explicit memory banks, architectural expansion, or auxiliary language models, resulting in substantial parameter growth and inference overhead. We introduce ReCap, a lightweight consistency framework that improves character stability and visual fidelity without modifying the base diffusion backbone. ReCap's CORE (COnditional frame REferencing) module treats anaphors, in our case pronouns, as visual anchors, activating only when characters are referred to by a pronoun and conditioning on the preceding frame to propagate visual identity. This selective design avoids unconditional cross-frame conditioning and introduces only 149K additional parameters, a fraction of the cost of memory-bank and LLM-augmented approaches. To further stabilize identity, we incorporate SemDrift (Guided Semantic Drift Correction) applied only during training. When text is vague or referential, the denoiser lacks a visual anchor for identity-defining attributes, causing character appearance to drift across frames, SemDrift corrects this by aligning denoiser representations with pretrained DINOv3 visual embeddings, enforcing semantic identity stability at zero inference cost. ReCap outperforms previous state-of-the-art, StoryGPT-V, on the two main benchmarks for story visualization by 2.63% Character-Accuracy on FlintstonesSV and by 5.65% on PororoSV, establishing a new state-of-the-art character consistency on both benchmarks. Furthermore, we extend story visualization to human-centric narratives derived from real films, demonstrating the capability of ReCap beyond stylized cartoon domains.

Related papers

• Sidecar: Training-Free Semantic Reuse for Character-Consistent Free-form Visual Storytelling [5.249739038963074]
  In free-form story generation, a character is fully described only when first introduced and is later referred to by a type-level mention or pronoun.<n>We propose textbfSidecar, a plug-and-play semantic augmentation module that preserves entity-level information from the initial description and injects the missing semantics into later prompt embeddings.<n>Experiments on FreeStoryBench show that Sidecar consistently improves prompt-image alignment and character consistency across multiple SDXL- and FLUX-based baselines, with negligible computational overhead.
  arXiv  Detail & Related papers  (2026-08-27T15:53:30Z)
• Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory [79.01059178883817]
  IAMFlow is a training-free identity-aware memory framework that explicitly models and tracks persistent entity identities.<n>A VLM asynchronously verifies and refines attributes from rendered frames, enabling explicit entity tracking in place of implicit similarity-based matching.<n>NarraStream-Bench is a benchmark for narrative streaming video generation that features 324 multi-prompt scripts spanning six dimensions.
  arXiv  Detail & Related papers  (2026-05-18T17:54:34Z)
• Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification [60.02530716177415]
  Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data.<n> Existing exemplar-free approaches largely rely on visual-only distillation or parameter regularization.<n>We propose Prompt-Anchored vision-text Distillation (PAD), an asymmetric vision-text framework for semantic alignment and cross-domain generalization.
  arXiv  Detail & Related papers  (2026-05-06T15:23:13Z)
• DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior [84.56343116275423]
  We introduce DreamShot, a video generative model based storyboard framework.<n>DreamShot exploits powerful video diffusion priors for controllable multi-shot synthesis.<n>It produces visually and semantically coherent sequences with improved narrative fidelity and character continuity.
  arXiv  Detail & Related papers  (2026-04-19T01:51:41Z)
• Directing the Narrative: A Finetuning Method for Controlling Coherence and Style in Story Generation [2.9255420892138306]
  We propose a two-stage framework designed for robust and consistent story generation.<n>First, we introduce Group-Shared Attention (GSA), a mechanism that fosters intrinsic consistency.<n>Second, we leverage Direct Preference Optimization (DPO) to align generated outputs with human aesthetic and narrative standards.
  arXiv  Detail & Related papers  (2026-03-18T02:43:02Z)
• CharCom: Composable Identity Control for Multi-Character Story Illustration [13.582635774872463]
  CharCom is a framework that achieves character-consistent story illustration through composable LoRA adapters.<n> Experiments on multi-scene narratives demonstrate that CharCom significantly enhances character fidelity, semantic alignment, and temporal coherence.<n>It remains robust in crowded scenes and enables scalable multi-character generation with minimal overhead, making it well-suited for real-world applications such as story illustration and animation.
  arXiv  Detail & Related papers  (2025-10-11T09:36:20Z)
• VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention [70.61101071902596]
  Current video generation models excel at short clips but fail to produce cohesive multi-shot narratives due to disjointed visual dynamics and fractured storylines.<n>We introduce VideoGen-of-Thought (VGoT), a step-by-step framework that automates multi-shot video synthesis from a single sentence.<n>VGoT generates multi-shot videos that outperform state-of-the-art baselines by 20.4% in within-shot face consistency and 17.4% in style consistency.
  arXiv  Detail & Related papers  (2025-03-19T11:59:14Z)
• 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)
• StoryGPT-V: Large Language Models as Consistent Story Visualizers [33.68157535461168]
  generative models have demonstrated impressive capabilities in generating realistic and visually pleasing images grounded on textual prompts.<n>Yet, the emerging Large Language Model (LLM) showcases robust reasoning abilities to navigate through ambiguous references.<n>We introduce emphStoryGPT-V, which leverages the merits of the latent diffusion (LDM) and LLM to produce images with consistent and high-quality characters.
  arXiv  Detail & Related papers  (2023-12-04T18:14:29Z)
• 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.