Scaling Non-Parametric Sampling with Representation

• URL: http://arxiv.org/abs/2510.22196v1
• Date: Sat, 25 Oct 2025 07:29:26 GMT
• Title: Scaling Non-Parametric Sampling with Representation
• Abstract summary: A simple, non-parametric generative model is proposed to strip away complicated engineering tricks.<n>Despite its minimal architecture, the model produces high-fidelity samples on MNIST and visually compelling CIFAR-10 images.<n>The model's white-box nature also allows us to have a mechanistic understanding of how the model generalizes and generates diverse images.
• Score: 8.813309990761686
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scaling and architectural advances have produced strikingly photorealistic image generative models, yet their mechanisms still remain opaque. Rather than advancing scaling, our goal is to strip away complicated engineering tricks and propose a simple, non-parametric generative model. Our design is grounded in three principles of natural images-(i) spatial non-stationarity, (ii) low-level regularities, and (iii) high-level semantics-and defines each pixel's distribution from its local context window. Despite its minimal architecture and no training, the model produces high-fidelity samples on MNIST and visually compelling CIFAR-10 images. This combination of simplicity and strong empirical performance points toward a minimal theory of natural-image structure. The model's white-box nature also allows us to have a mechanistic understanding of how the model generalizes and generates diverse images. We study it by tracing each generated pixel back to its source images. These analyses reveal a simple, compositional procedure for "part-whole generalization", suggesting a hypothesis for how large neural network generative models learn to generalize.

Related papers

• Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors [61.34273238077091]
  We present a novel method for generating orbital videos from a single image of an object.<n>Our method achieves superior visual quality, shape realism and multi-view consistency compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-04-14T05:35:46Z)
• Geometric Priors for Generalizable World Models via Vector Symbolic Architecture [9.216794073296679]
  Key challenge in artificial intelligence is understanding how neural systems learn representations that capture the underlying dynamics of the world.<n>We address these issues with a generalizable world model grounded in Vector Symbolic Architecture (VSA) principles as geometric priors.<n>We show how training to have latent group structure yields generalizable, data-efficient, and interpretable world models.
  arXiv  Detail & Related papers  (2026-02-25T00:41:42Z)
• Blur2Sharp: Human Novel Pose and View Synthesis with Generative Prior Refinement [6.91111219679588]
  Blur2Sharp is a novel framework integrating 3D-aware neural rendering and diffusion models to generate sharp, geometrically consistent novel-view images.<n>Our method employs a dual-conditioning architecture: first, a Human NeRF model generates geometrically coherent multi-view renderings for target poses, explicitly encoding 3D structural guidance.<n>We further enhance visual quality through hierarchical feature fusion, incorporating texture, normal, and semantic priors extracted from parametric SMPL models to simultaneously improve global coherence and local detail accuracy.
  arXiv  Detail & Related papers  (2025-12-09T03:49:12Z)
• HiCoGen: Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement Learning [66.99487505369254]
  HiCoGen is built upon a novel Chain of Synthesis paradigm.<n>It decomposes complex prompts into minimal semantic units.<n>It then synthesizes these units iteratively, where the image generated in each step provides crucial visual context for the next.<n>Experiments show our approach significantly outperforms existing methods in both concept coverage and compositional accuracy.
  arXiv  Detail & Related papers  (2025-11-25T06:24:25Z)
• Detecting the Undetectable: Combining Kolmogorov-Arnold Networks and MLP for AI-Generated Image Detection [0.0]
  This paper presents a novel detection framework adept at robustly identifying images produced by cutting-edge generative AI models. We propose a classification system that integrates semantic image embeddings with a traditional Multilayer Perceptron (MLP)
  arXiv  Detail & Related papers  (2024-08-18T06:00:36Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Images [79.39247661907397]
  We introduce an effective framework Generalizable Model-based Neural Radiance Fields to synthesize free-viewpoint images. Specifically, we propose a geometry-guided attention mechanism to register the appearance code from multi-view 2D images to a geometry proxy.
  arXiv  Detail & Related papers  (2023-03-24T03:32:02Z)
• Zero-1-to-3: Zero-shot One Image to 3D Object [30.455300183998247]
  We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image. Our conditional diffusion model uses a synthetic dataset to learn controls of the relative camera viewpoint. Our method significantly outperforms state-of-the-art single-view 3D reconstruction and novel view synthesis models by leveraging Internet-scale pre-training.
  arXiv  Detail & Related papers  (2023-03-20T17:59:50Z)
• Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion [54.151979979158085]
  We introduce a principled end-to-end reconstruction framework for natural images, where accurate ground-truth poses are not available. We leverage an unconditional 3D-aware generator, to which we apply a hybrid inversion scheme where a model produces a first guess of the solution. Our framework can de-render an image in as few as 10 steps, enabling its use in practical scenarios.
  arXiv  Detail & Related papers  (2022-11-21T17:42:42Z)
• Neural Knitworks: Patched Neural Implicit Representation Networks [1.0470286407954037]
  We propose Knitwork, an architecture for neural implicit representation learning of natural images that achieves image synthesis. To the best of our knowledge, this is the first implementation of a coordinate-based patch tailored for synthesis tasks such as image inpainting, super-resolution, and denoising. The results show that modeling natural images using patches, rather than pixels, produces results of higher fidelity.
  arXiv  Detail & Related papers  (2021-09-29T13:10:46Z)
• OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression [59.58879331876508]
  We study the learning of representation models for omnidirectional images and propose to use the properties of HEALPix uniform sampling of the sphere to redefine the mathematical tools used in deep learning models for omnidirectional images. Our proposed on-the-sphere solution leads to a better compression gain that can save 13.7% of the bit rate compared to similar learned models applied to equirectangular images.
  arXiv  Detail & Related papers  (2021-07-19T22:14:30Z)
• ExSinGAN: Learning an Explainable Generative Model from a Single Image [0.0]
  We propose a hierarchical framework that simplifies the learning of the intricate conditional distributions through the successive learning of the distributions about structure, semantics and texture. We design ExSinGAN composed of three cascaded GANs for learning an explainable generative model from a given image. ExSinGAN is learned not only from the internal patches of the given image as the previous works did, but also from the external prior obtained by the GAN inversion technique.
  arXiv  Detail & Related papers  (2021-05-16T04:38:46Z)
• Unsupervised Layered Image Decomposition into Object Prototypes [39.20333694585477]
  We present an unsupervised learning framework for decomposing images into layers of automatically discovered object models. We first validate our approach by providing results on par with the state of the art on standard multi-object synthetic benchmarks. We then demonstrate the applicability of our model to real images in tasks that include clustering (SVHN, GTSRB), cosegmentation (Weizmann Horse) and object discovery from unfiltered social network images.
  arXiv  Detail & Related papers  (2021-04-29T18:02:01Z)
• Counterfactual Generative Networks [59.080843365828756]
  We propose to decompose the image generation process into independent causal mechanisms that we train without direct supervision. By exploiting appropriate inductive biases, these mechanisms disentangle object shape, object texture, and background. We show that the counterfactual images can improve out-of-distribution with a marginal drop in performance on the original classification task.
  arXiv  Detail & Related papers  (2021-01-15T10:23:12Z)

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.