Högskolan i Skövde

his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Diffusion-based visual pathfinding: Reframing navigation as a generative task in game environments
University of Skövde, School of Informatics.
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Pathfinding is a fundamental task in game AI, traditionally solved through graph-based algorithms or reinforcement learning. However, these methods rely on symbolic representations and lack end-to-end visual generalization. This study explores a novel approach that reframes pathfinding as a generative task using diffusion models, where navigation is directly learned from visual inputs. Two architectures are investigated: Stable Diffusion, fine-tuned with LoRA on maze-path image pairs using an image-to-image pipeline; and AnimateDiff, a video-based diffusion model trained to generate path progression animations from maze inputs using both noise-to-video and image-to-video pipelines.

Experimental results demonstrate that Stable Diffusion fails to generate coherent or goal-directed paths, which highlights the limitations of static image transformation for structured tasks. Similarly, the image-to-video pipeline of AnimateDiff proves ineffective, which often disregards the input maze and producing hallucinated content. In contrast, the noise-to-video pipeline of AnimateDiff succeeds to generate plausible and visually consistent pathfinding sequences that align with the structure of A*-generated trajectories.

These findings suggest that AnimateDiff’s cross-frame attention mechanism is capable of capturing the co-evolution of map structure and path progression, but lacks the ability to condition path generation on a fixed, externally provided maze. This highlights both the potential and current limitations of diffusion-based visual planners, especially in tasks requiring spatial consistency between input and output domains.

Place, publisher, year, edition, pages
2024. , p. 60
National Category
Information Systems, Social aspects
Identifiers
URN: urn:nbn:se:his:diva-25375OAI: oai:DiVA.org:his-25375DiVA, id: diva2:1978336
Subject / course
Informationsteknologi
Educational program
Spelutveckling - masterprogram
Supervisors
Examiners
Available from: 2025-06-27 Created: 2025-06-27 Last updated: 2025-09-29Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
School of Informatics
Information Systems, Social aspects

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 77 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf