VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset

• URL: http://arxiv.org/abs/2605.23518v1
• Date: Fri, 22 May 2026 11:33:43 GMT
• Title: VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset
• Abstract summary: We introduce VINS-120K, the first large-scale dataset for instruction-based UHR image editing.<n>We develop a high-frequency-aware post-adaptation strategy to extend pretrained non-high-resolution models to the UHR regime.<n>Experiments confirm that our work improves fine-grained detail synthesis and texture realism in UHR image editing.
• Score: 35.077683100413076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Directly editing ultra-high-resolution (UHR) images is valuable but underexplored, primarily due to the lack of high-quality data and the challenge in modeling high-frequency texture details. We introduce VINS-120K, the first large-scale dataset for instruction-based UHR image editing, comprising 120K carefully curated triplets of instruction, input image, and edited image. Each image exceeds 4K resolution ($\geq$4096 $\times$ 4096) and is filtered through a rigorous multi-stage pipeline to ensure visual quality, instruction alignment, and aesthetic fidelity. Built on VINS-120K, we further develop a high-frequency-aware post-adaptation strategy to extend pretrained non-high-resolution models to the UHR regime. We also present VINS-4KEval, a benchmark covering diverse editing types, to facilitate consistent evaluation in UHR settings. Experiments confirm that our work improves fine-grained detail synthesis and texture realism in UHR image editing.

Related papers

• EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing [32.87034497388552]
  EditBridge is a diffusion bridge framework for efficient ultra high-resolution editing.<n>We introduce a prior-guided block-wise sparse attention mechanism that exploits semantic correspondence from first-stage editing to constrain cross-image interactions.<n>Experiments demonstrate that EditBridge achieves high-fidelity editing with superior perceptual quality at resolutions up to 4K, delivering 3.6--8.4$times$ speedup at 2K and enabling practical 4K editing in 61 seconds.
  arXiv  Detail & Related papers  (2026-08-18T17:53:16Z)
• Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing [11.862248587214951]
  This paper introduces UltraDiffEdit, a tuning-free image editing framework that extends latent diffusion models (LDMs) to ultrahigh resolutions.<n>We employ multi-patch encoding to preserve both edited and unedited visual details within the latent space.<n>We also introduce a patch-based hybrid sampling approach that captures local, intermediate, and global features, ensuring semantic coherence and enhancing fine detail during denoising.
  arXiv  Detail & Related papers  (2026-07-07T10:52:10Z)
• 4KLSDB: A Large-Scale Dataset for 4K Image Restoration and Generation [23.288582652884642]
  Current publicly available datasets lack both the native 4K resolution and the extensive scale necessary for training state-of-the-art models.<n>We introduce a 4K Large Scale dataset and Benchmark (4KLSDB) consisting of 129,484 carefully curated 4K resolution images spanning multiple categories.<n>We demonstrate 4KLSDB's effectiveness by training representative super-resolution and diffusion models, observing significant improvements on native 4K benchmarks.
  arXiv  Detail & Related papers  (2026-05-23T22:49:04Z)
• 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)
• Towards Ultra-High-Definition Image Deraining: A Benchmark and An Efficient Method [42.331058889312466]
  This paper contributes the first large-scale UHD image deraining dataset, 4K-Rain13k, that contains 13,000 image pairs at 4K resolution. We develop an effective and efficient vision-based architecture (UDR-Mixer) to better solve this task.
  arXiv  Detail & Related papers  (2024-05-27T11:45:08Z)
• Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey [116.29700317843043]
  This paper introduces a novel benchmark as part of the AIS 2024 Real-Time Image Super-Resolution Challenge. It aims to upscale compressed images from 540p to 4K resolution in real-time on commercial GPUs. We use a diverse test set containing a variety of 4K images ranging from digital art to gaming and photography.
  arXiv  Detail & Related papers  (2024-04-25T10:12:42Z)
• HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing [38.13162627140172]
  HQ-Edit is a high-quality instruction-based image editing dataset with around 200,000 edits. To ensure its high quality, diverse examples are first collected online, expanded, and then used to create high-quality diptychs. HQ-Edits high-resolution images, rich in detail and accompanied by comprehensive editing prompts, substantially enhance the capabilities of existing image editing models.
  arXiv  Detail & Related papers  (2024-04-15T17:59:31Z)
• Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation [51.26219245226384]
  Modern displays are capable of rendering video content with high dynamic range (WCG) and wide color gamut (SDR) The majority of available resources are still in standard dynamic range (SDR) We define and analyze the SDRTV-to-TV task by modeling the formation of SDRTV/TV content. Our method is primarily designed for ultra-high-definition TV content and is therefore effective and lightweight for processing 4K resolution images.
  arXiv  Detail & Related papers  (2023-09-08T02:50:54Z)
• HQ-50K: A Large-scale, High-quality Dataset for Image Restoration [105.22191357934398]
  HQ-50K contains 50,000 high-quality images with rich texture details and semantic diversity. We analyze existing image restoration datasets from five different perspectives. HQ-50K considers all of these five aspects during the data curation process and meets all requirements.
  arXiv  Detail & Related papers  (2023-06-08T17:44:21Z)
• Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing [71.62289021118983]
  We present an efficient baseline model ESDNet for tackling 4K moire images, wherein we build a semantic-aligned scale-aware module to address the scale variation of moire patterns. Our approach outperforms state-of-the-art methods by a large margin while being much more lightweight.
  arXiv  Detail & Related papers  (2022-07-20T14:20:52Z)
• One-shot Ultra-high-Resolution Generative Adversarial Network That Synthesizes 16K Images On A Single GPU [1.9060575156739825]
  OUR-GAN is a one-shot generative adversarial network framework that generates non-repetitive 16K images from a single training image. OUR-GAN can synthesize high-quality 16K images with 12.5 GB of GPU memory and 4K images with only 4.29 GB. OUR-GAN is the first one-shot image synthesizer that generates non-repetitive UHR images on a single consumer GPU.
  arXiv  Detail & Related papers  (2022-02-28T13:48:41Z)

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.