UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset

• URL: http://arxiv.org/abs/2510.20661v1
• Date: Thu, 23 Oct 2025 15:34:53 GMT
• Title: UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset
• Abstract summary: We introduce textbfUltraHR-100K, a high-quality dataset of 100K UHR images with rich captions, offering diverse content and strong visual fidelity.<n>We propose a frequency-aware post-training method that enhances fine-detail generation in T2I diffusion models.
• Score: 37.878145237462434
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ultra-high-resolution (UHR) text-to-image (T2I) generation has seen notable progress. However, two key challenges remain : 1) the absence of a large-scale high-quality UHR T2I dataset, and (2) the neglect of tailored training strategies for fine-grained detail synthesis in UHR scenarios. To tackle the first challenge, we introduce \textbf{UltraHR-100K}, a high-quality dataset of 100K UHR images with rich captions, offering diverse content and strong visual fidelity. Each image exceeds 3K resolution and is rigorously curated based on detail richness, content complexity, and aesthetic quality. To tackle the second challenge, we propose a frequency-aware post-training method that enhances fine-detail generation in T2I diffusion models. Specifically, we design (i) \textit{Detail-Oriented Timestep Sampling (DOTS)} to focus learning on detail-critical denoising steps, and (ii) \textit{Soft-Weighting Frequency Regularization (SWFR)}, which leverages Discrete Fourier Transform (DFT) to softly constrain frequency components, encouraging high-frequency detail preservation. Extensive experiments on our proposed UltraHR-eval4K benchmarks demonstrate that our approach significantly improves the fine-grained detail quality and overall fidelity of UHR image generation. The code is available at \href{https://github.com/NJU-PCALab/UltraHR-100k}{here}.

Related papers

• PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset [93.70328662327375]
  Text-to-Image (T2I) models have recently seen notable progress around 1K and 2K resolution.<n>Ultra-High-Resolution (UHR) image generation poses great challenges due to the scarcity and complexity of high-resolution content.<n>We introduce PixVerve-95K, a high-quality, open-source UHR T2I dataset curated with a carefully designed data pipeline.
  arXiv  Detail & Related papers  (2026-05-19T17:35:09Z)
• From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark [42.33679433467548]
  We introduce a progressive spectral decomposition for the restoration process, decomposing it into three stages: zero-frequency textbfenhancement, low-frequency textbfrestoration, and high-frequency textbfrefinement.<n>Our proposed methods demonstrate superior performance across a range of UHD image restoration tasks, and extensive ablation studies confirm the contribution and necessity of each module.
  arXiv  Detail & Related papers  (2026-04-17T03:13:56Z)
• LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts [48.279914726380376]
  textbfLUVE is a framework for ultra-high-resolution (UHR) video generation.<n>It employs a three-stage architecture for motion-consistent latent synthesis, video latent upsampling, and high-resolution content refinement.<n>LUVE achieves superior photorealism and content fidelity in UHR video generation, and comprehensive ablation studies further validate the effectiveness of each component.
  arXiv  Detail & Related papers  (2026-02-12T04:35:16Z)
• Enhancing Text-to-Image Generation via End-Edge Collaborative Hybrid Super-Resolution [6.015475364527398]
  We propose an end-edge collaborative generation-enhancement framework.<n> Experiments show that our system reduces service latency by 33% compared with baselines.
  arXiv  Detail & Related papers  (2026-01-21T07:55:37Z)
• UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers [58.37965214608629]
  We present UltraImage, a principled framework that addresses content repetition and quality degradation.<n>Experiments show that UltraImage consistently outperforms prior methods on Qwen-Image and Flux (around 4K) across three generation scenarios.<n>UltraImage can generate images up to 6K*6K without low-resolution guidance from a training resolution of 1328p, demonstrating its extreme extrapolation capability.
  arXiv  Detail & Related papers  (2025-12-04T06:24:04Z)
• Missing Fine Details in Images: Last Seen in High Frequencies [17.95197409468585]
  We propose a wavelet-based, frequency-aware variational autoencoder (FA-VAE) framework that explicitly decouples the optimization of low- and high-frequency components.<n>Our approach bridges the fidelity gap in current latent tokenizers and emphasizes the importance of frequency-aware optimization for realistic image synthesis.
  arXiv  Detail & Related papers  (2025-09-05T18:49:08Z)
• Stroke-based Cyclic Amplifier: Image Super-Resolution at Arbitrary Ultra-Large Scales [10.209274379479586]
  Prior Arbitrary-Scale Image Super-Resolution (ASISR) methods often experience a significant performance decline when the upsampling factor exceeds the range covered by the training data.<n>We propose a unified model, Stroke-based Cyclic Amplifier (SbCA), for ultra-large upsampling tasks.
  arXiv  Detail & Related papers  (2025-06-12T14:51:10Z)
• High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity [69.32473738284374]
  Diffusion models have revolutionized text-to-image synthesis by delivering exceptional quality, fine detail resolution, and strong contextual awareness.<n>We propose DiffDIS, a diffusion-driven segmentation model that taps into the potential of the pre-trained U-Net within diffusion models.<n>Experiments on the DIS5K dataset demonstrate the superiority of DiffDIS, achieving state-of-the-art results through a streamlined inference process.
  arXiv  Detail & Related papers  (2024-10-14T02:49:23Z)
• UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks [36.61645124563195]
  We present UltraPixel, a novel architecture utilizing cascade diffusion models to generate high-quality images at multiple resolutions. We use semantics-rich representations of lower-resolution images in the later denoising stage to guide the whole generation of highly detailed high-resolution images. Our model achieves fast training with reduced data requirements, producing photo-realistic high-resolution images.
  arXiv  Detail & Related papers  (2024-07-02T11:02:19Z)
• I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models [54.99771394322512]
  Video synthesis has recently made remarkable strides benefiting from the rapid development of diffusion models. It still challenges encounters in terms of semantic accuracy, clarity, and continuity-temporal continuity. We propose a cascaded I2VGen-XL approach that enhances model performance by decoupling these two factors. I2VGen-XL can simultaneously enhance the semantic accuracy, continuity of details and clarity of generated videos.
  arXiv  Detail & Related papers  (2023-11-07T17:16:06Z)
• Investigating Tradeoffs in Real-World Video Super-Resolution [90.81396836308085]
  Real-world video super-resolution (VSR) models are often trained with diverse degradations to improve generalizability. To alleviate the first tradeoff, we propose a degradation scheme that reduces up to 40% of training time without sacrificing performance. To facilitate fair comparisons, we propose the new VideoLQ dataset, which contains a large variety of real-world low-quality video sequences.
  arXiv  Detail & Related papers  (2021-11-24T18:58:21Z)
• Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning [62.52242684874278]
  Cross-modality distribution of spatial and spectral information makes the problem challenging. We propose a novel textitlightweight deep neural network-based framework, namely PZRes-Net. Our framework learns a high resolution and textitzero-centric residual image, which contains high-frequency spatial details of the scene.
  arXiv  Detail & Related papers  (2020-06-18T06:32:11Z)

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.