Coherence-Oriented Dream Scene Visualisation

Azra Açıl; Simon Colton

cs.AIAug 5, 2026

Coherence-Oriented Dream Scene Visualisation

Authors: Azra Açıl, Simon Colton

Organizations: School of Electronic Engineering and Computer Science, Queen Mary University of London, UK

Abstract

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.

Explore similar work

VoT: Vision-of-Thought for Unified Multimodal Representation Alignment
Sep 7, 2026Jingxiang Sun, Chao Liao, Zhengxiong Luo +6Vision-Language Alignment Multimodal Alignment
Can Language Models Imagine Without Seeing? Ekphrasis: Measuring Visual Creative Ideation in Text-Only LLMs
Aug 7, 2026Hongyu Luo, He Wang, Huihao Jing +6Visual Generation Creativity
Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm
May 12, 2026Yaofang Liu, Kangning Cui, Meng Chu +7Visual Generation Text-To-Image

Sep 7, 2026 · cs.CVJ/K move · Enter open · S save

VoT: Vision-of-Thought for Unified Multimodal Representation Alignment

Jingxiang Sun, Chao Liao, Zhengxiong Luo, Chaorui Deng+5

Current text-to-image systems typically employ a "text encoder plus diffusion decoder" paradigm, in which text semantics directly modulate continuous latent noise. Despite their success, these methods lack an explicit, interpretable intermediate representation that effectively bridges high-level linguistic semantics and low-level visual signals. In this paper, we propose Vision-of-Thought (VoT), a framework that introduces a discrete visual-thinking layer between vision-language models (VLMs) and diffusion transformers (DiTs). Instead of treating VLMs merely as text encoders, we use them as multimodal planners that generate discrete VoT tokens representing high-level visual plans, such as objects and layouts, before rendering pixels. We train a specialized VoT tokenizer in the VLM semantic space with a closed-loop objective that combines VLM alignment, feature reconstruction, and vector-quantization losses. These objectives make the tokens semantically readable by the VLM while preserving the visual information needed for generation. Experimental results demonstrate that VoT improves semantic alignment and provides a structured interface for interpretable and controllable generation.

Vision-Language Alignment Multimodal Alignment Visual Reasoning

Open paper Ask about it PDF

Abstract

Explore similar work

VoT: Vision-of-Thought for Unified Multimodal Representation Alignment

Can Language Models Imagine Without Seeing? Ekphrasis: Measuring Visual Creative Ideation in Text-Only LLMs

Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm