mlsanityData to 14 Oct 2026

UltraZoom: Generating Gigapixel Images from Regular Photos

arXiv 2506.13756 ↗First posted 16 Jun 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

We present UltraZoom, a system for generating gigapixel-resolution images of objects from casually captured inputs, such as handheld phone photos. Given a full-shot image (global, low-detail) and one or more close-ups (local, high-detail), UltraZoom upscales the full image to match the fine detail and scale of the close-up examples. To achieve this, we construct a per-instance paired dataset from the close-ups and adapt a pretrained generative model to learn object-specific low-to-high resolution mappings. At inference, we apply the model in a sliding window fashion over the full image. Constructing these pairs is non-trivial: it requires registering the close-ups within the full image for scale estimation and degradation alignment. We introduce a simple, robust method for getting registration on arbitrary materials in casual, in-the-wild captures. Together, these components form a system that enables seamless pan and zoom across the entire object, producing consistent, photorealistic gigapixel imagery from minimal input.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

25 of 42 references.

References · 25

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  3. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  4. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  5. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  6. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 536
  7. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  8. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 403
  9. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  10. 2017Toward Multimodal Image-to-Image Translationcited by 296
  11. 2019Meta-SR: A Magnification-Arbitrary Network for Super-Resolutioncited by 181
  12. 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 174
13 more
  1. 2019Image Super-Resolution by Neural Texture Transfercited by 120
  2. 2019Zoom To Learn, Learn To Zoomcited by 115
  3. 2018CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warpingcited by 91
  4. 2021MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolutioncited by 80
  5. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72
  6. 2021UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolutioncited by 57
  7. 2017Learning Texture Manifolds with the Periodic Spatial GANcited by 53
  8. 2017TextureGAN: Controlling Deep Image Synthesis with Texture Patchescited by 47
  9. 2021Dual-Camera Super-Resolution with Aligned Attention Modulescited by 34
  10. 2020Perceptual Extreme Super Resolution Network with Receptive Field Blockcited by 15
  11. 2021Attention-based Multi-Reference Learning for Image Super-Resolutioncited by 12
  12. 2024Infinite Texture: Text-guided High Resolution Diffusion Texture Synthesiscited by 5
  13. 2024EarthGen: Generating the World from Top-Down Viewscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026MicroZoom: Structure-Preserving Detail Synthesis at Extreme Scalecited by 0
  2. 2026BigCell: Generating Gigapixel Whole-Slide Imagescited by 0