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
학습 가능한 대표 (LRs)는 다양한 종류의 신호에 대한 파라미터적 기능 가족을 조정할 수 있습니다. 이러한 신경 원주민 데이터 형식은 그들의 컴팩트성, 해상도-agnosticism 및 직접 신경 처리에 적합성 때문에 과학 커뮤니티에 관심을 모으고 있습니다. 반면에, gigapixel 이미지는 다양한 과학, 문화 및 산업 영역에 걸쳐 점점 더 널리 퍼져 있습니다. 이 논문에서, 우리는 GigaBench, gigapixel 이미지를 사용하여 LR를 배포하는 데 초점을 맞춘 최초의 벤치마크 및 실험적 평가를 소개합니다. GigaBench는 수집, 획득, 그리고 다양한 영역에 걸쳐 합성적으로 렌더링 된 이미지를 포함하고 있으며 이미지 압축 및 슈퍼 해상도에 적응
Machine translation (Meta M2M100); the English original follows.
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)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31644, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange