Moore, Escher, Penrose: A Conformal Golden Braid
Not on the map. Why?
Abstract (arXiv)
I don't think I have ever done anything as peculiar in my life. Among other things, it shows a young man looking with interest at a print on the wall of an exhibition that features himself. How can this be? Perhaps I am not far removed from Einstein's curved universe.'' So wrote M.C. Escher about his 1956 lithograph Print Gallery. Nearly half a century later, a mathematical analysis related its geometry to an untwisted source image through a conformal power map z mapsto zα, α ∈ mathbbC. Building on this construction, we use a frozen text-to-image diffusion model to generate new self-referential scenes. Prompting alone does not enforce the recursion, while a post-hoc transformation can leave structures poorly connected. Applying the transformation during sampling is also insufficient: the denoiser may "repair" the intended distortion or drift out of the prescribed geometry. We construct a generalized inverse T^dagger of the non-invertible image transformation T, adapted to its recursive constraint. In the idealized formulation, the Penrose identity TT^dagger T = T makes TT^dagger an idempotent projection onto geometrically admissible images. Yet denoising only the transformed image remains an out-of-distribution task, even with projection. We therefore braid denoising steps with T and T^dagger: source-space steps develop the untwisted scene, while transformed-space steps refine its appearance and connections in the final geometry. We generate Print Gallery-like compositions and explore further transformations. Rather than distorting a finished image, we let the scene and its distortion develop together.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 39 references that are in the map. First posted on arXiv 1 Oct 2026.
Builds on
22 of 39 references.
References · 22
- 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
- 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
- 2022Denoising Diffusion Restoration Modelscited by 951
- 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
- 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 529
- 2023Universal Guidance for Diffusion Modelscited by 426
- 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305
- 2023Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Modelscited by 46
- 2023Diffusion Illusions: Hiding Images in Plain Sightcited by 26
- 2024SyncTweedies: A General Generative Framework Based on Synchronized Diffusionscited by 26
- 2023Idempotent Generative Networkcited by 17
- 2023Generative Powers of Tencited by 15
10 more
- 2024ZoomLDM: Latent Diffusion Model for multi-scale image generationcited by 15
- 2024Fast constrained sampling in pre-trained diffusion modelscited by 9
- 2024Tiled Diffusioncited by 9
- 2025LookingGlass: Generative Anamorphoses via Laplacian Pyramid Warpingcited by 7
- 2022Self-Similarity Priors: Neural Collages as Differentiable Fractal Representationscited by 6
- 2023Generative Escher Meshescited by 5
- 2021Generalized Inversion of Nonlinear Operatorscited by 2
- 2025Refracting Reality: Generating Images with Realistic Transparent Objectscited by 2
- 2026Pseudo-Invertible Neural Networkscited by 2
- 2022Comparison of CoModGANs, LaMa and GLIDE for Art Inpainting- Completing M.C Escher's Print Gallerycited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later
- 2022Inversion-Based Style Transfer with Diffusion Models
- 2024Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting
- 2023Inversion-by-Inversion: Exemplar-based Sketch-to-Photo Synthesis via Stochastic Differential Equations without Training
- 2023Image Inpainting via Tractable Steering of Diffusion Models
- 2022Generative Modelling With Inverse Heat Dissipation
- 2023Reference-based Painterly Inpainting via Diffusion: Crossing the Wild Reference Domain Gap
- 2026Inverting Data Transformations via Diffusion Sampling