UltraZoom: Generating Gigapixel Images from Regular Photos

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ma, Jingwei, Jayaram, Vivek, Curless, Brian, Kemelmacher-Shlizerman, Ira, Seitz, Steven M.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916866556952576
author Ma, Jingwei
Jayaram, Vivek
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steven M.
author_facet Ma, Jingwei
Jayaram, Vivek
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steven M.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13756
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UltraZoom: Generating Gigapixel Images from Regular Photos
Ma, Jingwei
Jayaram, Vivek
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steven M.
Computer Vision and Pattern Recognition
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.
title UltraZoom: Generating Gigapixel Images from Regular Photos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.13756