mlsanityData to 14 Oct 2026

Coherence-Oriented Dream Scene Visualisation

arXiv 2608.05233 ↗First posted 5 Aug 2026cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Dreams can be emotionally intense but difficult to communicate. We describe the Dream Scene Visualiser (DSV) system which turns written dream descriptions into a temporal sequence of four panel images visualising the dream. This starts with a large language model prompted to split a dream description into four chronological parts. Then a text-to-image model produces images for each part with visual coherence maintained across the sequence, and DSV regenerates any image not suitably matching the text. We evaluate DSV over 50 visualisations from dream descriptions in DreamBank, and report quality, fidelity and coherence results via objective measures employing the CLIP, DINOv2 and Qwen2-VL vision-language models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 18 references that are in the map. First posted on arXiv 5 Aug 2026.

Builds on

11 of 18 references.

References · 11

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  7. 2022StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuationcited by 74
  8. 2024DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusioncited by 47
  9. 2024Creative Beam Search: LLM-as-a-Judge For Improving Response Generationcited by 14
  10. 2025Making Your Dreams A Reality: Decoding the Dreams into a Coherent Video Story from fMRI Signalscited by 2
  11. 2025DreamLLM-3D: Affective Dream Reliving using Large Language Model and 3D Generative AIcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
  2. 2026Humans vs Vision-Language Models: A Unified Measure of Narrative Coherence
  3. 2026DREAM: Extending Vision-Language Models with Dual-Objective Encoding for Cross-Modal Retrieval
  4. 2024Dreaming Out Loud: A Self-Synthesis Approach For Training Vision-Language Models With Developmentally Plausible Data
  5. 2024Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination
  6. 2026Dream2Learn: Structured Generative Dreaming for Continual Learning
  7. 2024Surrealistic-like Image Generation with Vision-Language Models
  8. 2024VORD: Visual Ordinal Calibration for Mitigating Object Hallucinations in Large Vision-Language Models