RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations

• URL: http://arxiv.org/abs/2605.15908v1
• Date: Fri, 15 May 2026 12:45:17 GMT
• Title: RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations
• Abstract summary: Continuous neural fields enable resolution-free rendering, but prior methods introduce continuity only at the decoding stage as an Natural Pixel module.<n>We propose RaPD, which performs diffusion in a continuous Neural Image Field (NIF) latent space.<n> Experiments demonstrate superior generation quality and resolution scalability.
• Score: 33.8420570329911
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Natural images are continuous, yet most generative models synthesize them on discrete grids, limiting resolution-flexible generation. Continuous neural fields enable resolution-free rendering, but prior methods introduce continuity only at the decoding stage as an interpolation module, leaving the generative latent space discretized and reconstruction-oriented. We propose RaPD (Resolution-agnostic Pixel Diffusion), which performs diffusion in a continuous Neural Image Field (NIF) latent space. RaPD bridges this reconstruction-generation gap with Semantic Representation Guidance for generation-aware latent learning and a Coordinate-Queried Attention Renderer for coordinate-conditioned, scale-aware rendering. A single denoised latent can be rendered at arbitrary resolutions by changing only the query coordinates, keeping diffusion cost fixed. Experiments demonstrate superior generation quality and resolution scalability.

Related papers

• Local Epistemic Uncertainty Guided Active Sampling for Plug-and-play Diffusive Image Restoration [15.371827475537776]
  Local Epistemic Uncertainty Guided Active Sampling framework is developed.<n>It balances detail preservation and artifact suppression in the spatial domain.<n>It reduces sampling time with negligible memory overhead.
  arXiv  Detail & Related papers  (2026-08-07T09:00:20Z)
• Hybrid-Domain Posterior Sampling for Inverse Problems via Latent Flow Matching [22.663919850054928]
  Hybrid-Domain Posterior Sampling (HDPS) is a decoupled inference framework that disentangles physical measurement consistency from semantic prior modeling.<n> Experiments on diverse inverse problems demonstrate that HDPS establishes a new state-of-the-art, successfully recovering the high-frequency structural precision that latent-only solvers inherently discard.
  arXiv  Detail & Related papers  (2026-08-01T08:46:12Z)
• Rarity-Aware Discrete Diffusion with Spatially Consistent Decoding for Photo-Realistic Image Super-Resolution [80.28905986756685]
  DiMOO-SR is a rarity-aware multimodal discrete diffusion framework for photo-realistic image Super-Resolution.<n>Experiments on widely used real-world SR benchmarks demonstrate that DiMOO-SR achieves competitive perceptual quality with only a few parallel decoding steps.
  arXiv  Detail & Related papers  (2026-07-20T07:01:01Z)
• Pixel-Space Diffusion Transformers [29.08838156660683]
  Latent diffusion models (LDMs) enable efficient high-resolution image synthesis by denoising in a VAE-compressed latent space.<n>This paper reviews Pixel-Space Diffusion Transformers (pDiTs) from the perspectives of model architecture, continuous generative mechanisms, and unified multimodal modeling.
  arXiv  Detail & Related papers  (2026-07-20T06:04:08Z)
• Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation [36.41177812868683]
  Latent diffusion models excel at generating high-quality images but lose the benefits of end-to-end modeling.<n>We propose Latent Forcing, a simple modification to existing architectures that achieves the efficiency of latent diffusion while operating on raw natural images.<n>Latent Forcing achieves a new state-of-the-art for diffusion transformer-based pixel generation at our compute scale.
  arXiv  Detail & Related papers  (2026-02-11T22:09:58Z)
• PosDiffAE: Position-aware Diffusion Auto-encoder For High-Resolution Brain Tissue Classification Incorporating Artifact Restoration [0.5442686600296733]
  We devise a mechanism to structure the latent space of a diffusion auto-encoding model, towards recognizing region-specific cellular patterns in brain images.<n>We also devise an unsupervised tear artifact restoration technique based on neighborhood awareness, utilizing latent representations and the constrained generation capability of diffusion models during inference.
  arXiv  Detail & Related papers  (2025-07-03T07:58:53Z)
• LatentINDIGO: An INN-Guided Latent Diffusion Algorithm for Image Restoration [19.74964267336191]
  We introduce a wavelet-inspired invertible neural network (INN) that simulates degradations through a forward transform and reconstructs lost details via the inverse transform.<n>Our algorithm achieves state-of-the-art performance on synthetic and real-world low-quality images, and can be readily adapted to arbitrary output sizes.
  arXiv  Detail & Related papers  (2025-05-19T10:17:16Z)
• Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling [50.34513854725803]
  Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors.<n>We propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-03-09T13:43:57Z)
• Timestep-Aware Diffusion Model for Extreme Image Rescaling [47.89362819768323]
  We propose a novel framework called Timestep-Aware Diffusion Model (TADM) for extreme image rescaling.<n>TADM performs rescaling operations in the latent space of a pre-trained autoencoder.<n>It effectively leverages powerful natural image priors learned by a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-08-17T09:51:42Z)
• Mitigating Data Consistency Induced Discrepancy in Cascaded Diffusion Models for Sparse-view CT Reconstruction [4.227116189483428]
  This study introduces a novel Cascaded Diffusion with Discrepancy Mitigation framework. It includes the low-quality image generation in latent space and the high-quality image generation in pixel space. It minimizes computational costs by moving some inference steps from pixel space to latent space.
  arXiv  Detail & Related papers  (2024-03-14T12:58:28Z)
• Improving Diffusion-Based Image Synthesis with Context Prediction [49.186366441954846]
  Existing diffusion models mainly try to reconstruct input image from a corrupted one with a pixel-wise or feature-wise constraint along spatial axes. We propose ConPreDiff to improve diffusion-based image synthesis with context prediction. Our ConPreDiff consistently outperforms previous methods and achieves a new SOTA text-to-image generation results on MS-COCO, with a zero-shot FID score of 6.21.
  arXiv  Detail & Related papers  (2024-01-04T01:10:56Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields [57.61024735931613]
  Recent approaches to arbitrary-scale single image super-resolution (ASR) use neural fields to represent continuous signals that can be sampled at arbitrary resolutions.<n>Existing methods attempt to mitigate this by approximating an integral version of the field at each scaling factor, compromising both fidelity and generalization.<n>We introduce neural heat fields, a novel neural field formulation that inherently models a physically exact PSF.<n>Our formulation enables analytically correct anti-aliasing at any desired output resolution, and -- unlike supersampling -- at no additional cost.
  arXiv  Detail & Related papers  (2023-11-29T14:01:28Z)
• InfinityGAN: Towards Infinite-Resolution Image Synthesis [92.40782797030977]
  We present InfinityGAN, a method to generate arbitrary-resolution images. We show how it trains and infers patch-by-patch seamlessly with low computational resources.
  arXiv  Detail & Related papers  (2021-04-08T17:59:30Z)

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.