Newest papers

GigaBench: Benchmarking Learnable Representations for Gigapixel Image Compression and Super-Resolution

Matteo Fusconi, Alex Costanzino, Pierluigi Zama Ramirez, Luigi Di Stefano · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31644 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Las Representaciones Aprendibles (LRs) pueden ajustar familias paramétricas de funciones a diversos tipos de señales. Estos formatos de datos neural-nativos emergentes están reuniendo interés en la comunidad científica debido a su compacidad, agnosticismo de resolución y agilidad para el procesamiento neural directo. Por otro lado, las imágenes de gigapíxeles se están convirtiendo cada vez más extendidas a través de una variedad de dominios científicos, culturales e industriales. En este artículo, presentamos GigaBench, el primer benchmark y evaluación experimental enfocado en el despliegue de LRs con imágenes de gigapíxeles. GigaBench incluye imágenes recopiladas, adquiridas y sintetizadas en diversos dominios, y aborda la compresión de imagen y la superresolución. Sugerimos un conjunto represent

Machine translation (Meta M2M100); the English original follows.

Abstract

Learnable Representations (LRs) can fit parametric families of functions to diverse kinds of signals. These emergent neural-native data formats are gathering interest in the scientific community due to their compactness, resolution-agnosticism and amenability to direct neural processing. On the other hand, gigapixel images are becoming increasingly widespread across a variety of scientific, cultural, and industrial domains. In this paper, we present GigaBench, the first benchmark and experimental evaluation focused on deploying LRs with gigapixel imagery. GigaBench includes images collected, acquired, and synthetically rendered across diverse domains, and addresses image compression and super-resolution. We adapt a representative set of LRs, spanning Implicit, Hybrid, and Explicit methods, so as to operate reliably at the gigapixel scale on consumer hardware. Through systematic evaluation across reconstruction quality, model size, compression and inference times, we identify consistent trends across methods and suggest actionable guidance for future investigation.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Benchmarking, Image compression, Set (abstract data type), Artificial intelligence, Benchmark (surveying)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange