computer-vision-5

Spectral Reconstruction

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-reconstruction-5

Trend

Dataset

Best Model

Actions

ARAD-1K

Real HSI

KAIST

Libraries

i

Use these libraries to find spectral-reconstruction-5 models and implementations

swz30/MPRNet

3 papers 1,161

Datasets

Subtasks

No subtasks available.

Most implemented papers

Enhanced Deep Residual Networks for Single Image Super-Resolution

Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, Kyoung Mu Lee•Sun Jul 09 2017

This paper develops an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods, and proposes a new multi-scale deepsuper-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model.

6646

Content

CAVE

swz30/MIRNet

3 papers 659

swz30/CycleISP

3 papers 503

swz30/mirnetv2

3 papers 402

cmhungsteve/Awesome-Transformer-Att…

2 papers 4,540

0

Paper Graph

Learning Enriched Features for Real Image Restoration and Enhancement

Munawar Hayat, Syed Waqas Zamir, Ming-Hsuan Yang, Aditya Arora, Salman H. Khan, Fahad Shahbaz Khan, Ling Shao•Sat Mar 14 2020

This paper presents a novel architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network and receiving strong contextual information from the low- resolution representations, named as MIRNet.

856 0

Paper Graph

Restormer: Efficient Transformer for High-Resolution Image Restoration

Salman Hameed Khan, Munawar Hayat, Ming-Hsuan Yang, Syed Waqas Zamir, F. Khan, Aditya Arora•Wed Nov 17 2021

This work proposes an efficient Transformer model by making several key designs in the building blocks (multi-head attention and feed-forward network) such that it can capture long-range pixel interactions, while still remaining applicable to large images.

3334 0

Paper Graph

Multi-Stage Progressive Image Restoration

Ling Shao, Salman Hameed Khan, Munawar Hayat, Syed Waqas Zamir, F. Khan, Ming-Hsuan Yang, Aditya Arora•Wed Feb 03 2021

This paper proposes a novel synergistic design that can optimally balance these competing goals in image restoration tasks, that progressively learns restoration functions for the degraded inputs, thereby breaking down the overall recovery process into more manageable steps.

1950 0

Paper Graph

Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction

L. Gool, Radu Timofte, Haoqian Wang, Yuanhao Cai, Jing Lin, Xiaowan Hu, Xin Yuan, Yulun Zhang•Sun Nov 14 2021

A novel framework, Mask-guided Spectral-wise Transformer (MST), that treats each spectral feature as a token and calculates self-attention along the spectral dimension and significantly outperforms state-of-the-art (SOTA) methods on simulation and real HSI datasets while requiring dramatically cheaper computational and memory costs.

349 0

Paper Graph

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 0

Paper Graph

StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization

Ahmed Mustafa, N. Pia, Guillaume Fuchs•Mon Nov 02 2020

StyleMelGAN is a lightweight neural vocoder allowing synthesis of high-fidelity speech with low computational complexity, and MUSHRA and P.800 listening tests show that StyleMelGAN outperforms prior neural vocoders in copy-synthesis and Text-to-Speech scenarios.

91 0

Paper Graph

HINet: Half Instance Normalization Network for Image Restoration

Liangyu Chen, J. Zhang, Xin Lu, Xiaojie Chu, Chengpeng Chen•Wed May 12 2021

A novel block is presented: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration networks and a simple and powerful multi-stage network named HINet is designed, which surpasses the state-of-the-art (SOTA) on various image restoration tasks.

607 0

Paper Graph

HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging

L. Gool, Radu Timofte, Haoqian Wang, Yuanhao Cai, Jing Lin, Xiaowan Hu, Xin Yuan, Yulun Zhang•Thu Mar 03 2022

A high-resolution dual-domain learning network (HDNet) for HSI reconstruction with HR pixel-level attention and frequency-level refinement that achieves SOTA performance on simulated and real HSI datasets.

209 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

Adding a benchmark result helps the community track progress.