Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry

• URL: http://arxiv.org/abs/2206.00106v1
• Date: Tue, 31 May 2022 20:39:56 GMT
• Title: Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry
• Authors: Miguel Gonz\'alez-Duque, Rasmus Berg Palm, S{\o}ren Hauberg, Sebastian Risi
• Abstract summary: We propose a method for reliable and random walks in the latent spaces of Categorical VAEs. We test our method with "Super Mario Bros" and "The Legend of Zelda" levels. Results show that the geometry we propose is better able to interpolate and sample, reliably staying closer to parts of the latent space that decode to playable content.
• Score: 7.863826008567604
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Deep generative models can automatically create content of diverse types. However, there are no guarantees that such content will satisfy the criteria necessary to present it to end-users and be functional, e.g. the generated levels could be unsolvable or incoherent. In this paper we study this problem from a geometric perspective, and provide a method for reliable interpolation and random walks in the latent spaces of Categorical VAEs based on Riemannian geometry. We test our method with "Super Mario Bros" and "The Legend of Zelda" levels, and against simpler baselines inspired by current practice. Results show that the geometry we propose is better able to interpolate and sample, reliably staying closer to parts of the latent space that decode to playable content.

Related papers

• Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata [70.9375320609781]
  We aim to generate fine-grained 3D geometry from large-scale sparse LiDAR scans, abundantly captured by autonomous vehicles (AV) We propose hierarchical Generative Cellular Automata (hGCA), a spatially scalable 3D generative model, which grows geometry with local kernels following, in a coarse-to-fine manner, equipped with a light-weight planner to induce global consistency.
  arXiv  Detail & Related papers  (2024-06-12T14:56:56Z)
• Unsupervised Representation Learning for Diverse Deformable Shape Collections [30.271818994854353]
  We introduce a novel learning-based method for encoding and manipulating 3D surface meshes. Our method is specifically designed to create an interpretable embedding space for deformable shape collections.
  arXiv  Detail & Related papers  (2023-10-27T13:45:30Z)
• Zero-Shot 3D Shape Correspondence [67.18775201037732]
  We propose a novel zero-shot approach to computing correspondences between 3D shapes. We exploit the exceptional reasoning capabilities of recent foundation models in language and vision. Our approach produces highly plausible results in a zero-shot manner, especially between strongly non-isometric shapes.
  arXiv  Detail & Related papers  (2023-06-05T21:14:23Z)
• SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry [92.24144643757963]
  3D indoor scenes are widely used in computer graphics, with applications ranging from interior design to gaming to virtual and augmented reality. High-quality 3D indoor scenes are highly demanded while it requires expertise and is time-consuming to design high-quality 3D indoor scenes manually. We propose SCENEHGN, a hierarchical graph network for 3D indoor scenes that takes into account the full hierarchy from the room level to the object level, then finally to the object part level. For the first time, our method is able to directly generate plausible 3D room content, including furniture objects with fine-grained geometry, and
  arXiv  Detail & Related papers  (2023-02-16T15:31:59Z)
• On Linking Level Segments [3.04585143845864]
  We present a Markov chain and a tree search algorithm that finds a link between two level segments. This method reliably finds links between segments and is customizable to meet a designer's needs.
  arXiv  Detail & Related papers  (2022-03-09T21:32:41Z)
• Differentiable Convolution Search for Point Cloud Processing [114.66038862207118]
  We propose a novel differential convolution search paradigm on point clouds. It can work in a purely data-driven manner and thus is capable of auto-creating a group of suitable convolutions for geometric shape modeling. We also propose a joint optimization framework for simultaneous search of internal convolution and external architecture, and introduce epsilon-greedy algorithm to alleviate the effect of discretization error.
  arXiv  Detail & Related papers  (2021-08-29T14:42:03Z)
• Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations Using a GAN [5.144809478361604]
  We propose a new hybrid approach that evolves CPPNs first, but allows the latent vectors to evolve later, and combines the benefits of both approaches. These approaches are evaluated in Super Mario Bros. and The Legend of Zelda.
  arXiv  Detail & Related papers  (2021-05-27T06:27:19Z)
• Quadric hypersurface intersection for manifold learning in feature space [52.83976795260532]
  manifold learning technique suitable for moderately high dimension and large datasets. The technique is learned from the training data in the form of an intersection of quadric hypersurfaces. At test time, this manifold can be used to introduce an outlier score for arbitrary new points.
  arXiv  Detail & Related papers  (2021-02-11T18:52:08Z)
• Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network [11.055580854275474]
  We show how designers may specify gameplay measures to our system and extract high-quality (playable) levels with a diverse range of level mechanics. An online user study shows how the different mechanics of the automatically generated levels affect subjective ratings of their perceived difficulty and appearance.
  arXiv  Detail & Related papers  (2020-07-11T03:38:06Z)
• Deep Geometric Texture Synthesis [83.9404865744028]
  We propose a novel framework for synthesizing geometric textures. It learns texture statistics from local neighborhoods of a single reference 3D model. Our network displaces mesh vertices in any direction, enabling synthesis of geometric textures.
  arXiv  Detail & Related papers  (2020-06-30T19:36:38Z)
• Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning [9.697217570243845]
  Recent procedural content generation via machine learning (PCGML) methods allow learning to produce similar content from existing content. It is an open questions how well these approaches can capture large-scale visual patterns such as symmetry. In this paper, we propose to match-three games as a domain to test PCGML algorithms regarding their ability to generate suitable patterns.
  arXiv  Detail & Related papers  (2020-05-26T08:58:37Z)

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.