computer-vision

Spectral Super-Resolution

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in spectral-super-resolution

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find spectral-super-resolution models and implementations

Intelligent-Imaging-Center/Spectral…

2 papers 67

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction

H. Pfister, L. Gool, Radu Timofte, Zudi Lin, Haoqian Wang, Jing Lin, Yulun Zhang•Sat Apr 16 2022

This work proposes a novel Transformer-based method, Multi-stage Spectral-wise Transformer (MST++), for efficient spectral reconstruction that significantly outperforms other state-of-the-art methods.

276

Content

0

Paper Graph

An efficient CNN for spectral reconstruction from RGB images

Radu Timofte, Y. Can•Wed Apr 11 2018

A moderately deep CNN model is proposed and substantially improve the reported performance on three spectral reconstruction standard benchmarks: ICVL, CAVE, and NUS.

64 0

Paper Graph

HPRN: Holistic Prior-Embedded Relation Network for Spectral Super-Resolution

Qian Du, Chaoxiong Wu, Jiaojiao Li, Rui Song, Yunsong Li•Tue Dec 28 2021

This article proposes a novel holistic prior-embedded relation network (HPRN) to integrate comprehensive priors to regularize and optimize the solution space of SSR and develops a transformer-based channel relation module (TCRM), which breaks the habit of employing scalars as the descriptors of channelwise relations in the previous deep feature prior.

34 0

Paper Graph

Learned Spectral Super-Resolution

Silvano Galliani, K. Schindler, E. Baltsavias, Charis Lanaras, D. Marmanis•Mon Mar 27 2017

A novel method for blind, single-image spectral super-resolution, which starts from the conjecture that it can learn the statistics of natural image spectra, and with its help generate finely resolved hyper-spectral images from RGB input.

138 0

Paper Graph

Frequency Estimation Using Complex-Valued Shifted Window Transformer

Josiah W. Smith, Murat Torlak•Sat Sep 16 2023

1-D real-valued and complex-valued shifted window (Swin) transformers, referred to as SwinFreq and CVSwinFreq, respectively, are introduced for line-spectra frequency estimation on 1-D complex-valued signals to validate the numerical and empirical superiority of SwinFreq and CVSwinFreq to the state-of-the-art deep-learning-based techniques and traditional frequency estimation algorithms.

6 0

Paper Graph

Model-Guided Network With Cluster-Based Operators for Spatio-Spectral Super-Resolution

Ivan Pereira-S'anchez, Julia Navarro, Ana Bel'en Petro, Joan Duran•Thu May 29 2025

An end-to-end model-driven framework that explicitly decomposes the joint spatio-spectral super-resolution problem into spatial super-resolution, spectral super-resolution and fusion tasks is proposed and an efficient nonlocal post-processing step that leverages image self-similarity by combining a multi-head attention mechanism with residual connections is introduced.

1 0

Paper Graph

Adding a benchmark result helps the community track progress.