Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Peng, Long, Wu, Anran, Li, Wenbo, Xia, Peizhe, Dai, Xueyuan, Zhang, Xinjie, Di, Xin, Sun, Haoze, Pei, Renjing, Wang, Yang, Cao, Yang, Zha, Zheng-Jun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909532353986560
author Peng, Long
Wu, Anran
Li, Wenbo
Xia, Peizhe
Dai, Xueyuan
Zhang, Xinjie
Di, Xin
Sun, Haoze
Pei, Renjing
Wang, Yang
Cao, Yang
Zha, Zheng-Jun
author_facet Peng, Long
Wu, Anran
Li, Wenbo
Xia, Peizhe
Dai, Xueyuan
Zhang, Xinjie
Di, Xin
Sun, Haoze
Pei, Renjing
Wang, Yang
Cao, Yang
Zha, Zheng-Jun
contents Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained to fixed-scale factors (\textit{e.g.}, $\times$ 2). Recent advances leveraging implicit neural representation (INR) have achieved great progress by modeling coordinate-to-pixel mappings. However, the efficiency of these methods may suffer from repeated upsampling and decoding, while their reconstruction fidelity and quality are constrained by the intrinsic representational limitations of coordinate-based functions. To address these challenges, we propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting. This approach eliminates the need for time-consuming upsampling and decoding, enabling extremely fast arbitrary-scale super-resolution. Once the Gaussian field is built in a single pass, ContinuousSR can perform arbitrary-scale rendering in just 1ms per scale. Our method introduces several key innovations. Through statistical ana
format Preprint
id arxiv_https___arxiv_org_abs_2503_06617
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling
Peng, Long
Wu, Anran
Li, Wenbo
Xia, Peizhe
Dai, Xueyuan
Zhang, Xinjie
Di, Xin
Sun, Haoze
Pei, Renjing
Wang, Yang
Cao, Yang
Zha, Zheng-Jun
Computer Vision and Pattern Recognition
Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained to fixed-scale factors (\textit{e.g.}, $\times$ 2). Recent advances leveraging implicit neural representation (INR) have achieved great progress by modeling coordinate-to-pixel mappings. However, the efficiency of these methods may suffer from repeated upsampling and decoding, while their reconstruction fidelity and quality are constrained by the intrinsic representational limitations of coordinate-based functions. To address these challenges, we propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting. This approach eliminates the need for time-consuming upsampling and decoding, enabling extremely fast arbitrary-scale super-resolution. Once the Gaussian field is built in a single pass, ContinuousSR can perform arbitrary-scale rendering in just 1ms per scale. Our method introduces several key innovations. Through statistical ana
title Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.06617