HyperAIHyperAI초신경
홈플랫폼문서뉴스연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAIHyperAI초신경

Command Palette

Search for a command to run...

Image Super Resolution On Urban100 4X

평가 지표

PSNR
SSIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

Paper TitleRepository
Hi-IR-L28.720.8514Hierarchical Information Flow for Generalized Efficient Image Restoration-
DRCT-L28.700.8508DRCT: Saving Image Super-resolution away from Information Bottleneck
HMA†28.690.8512HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
HAT-L28.600.8498Activating More Pixels in Image Super-Resolution Transformer
HAT_FIR28.43-SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
DRCT28.400.8457DRCT: Saving Image Super-resolution away from Information Bottleneck
HAT28.370.8447Activating More Pixels in Image Super-Resolution Transformer
CPAT+28.330.8425Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution-
CPAT28.220.8408Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution-
IPG28.130.8392Image Processing GNN: Breaking Rigidity in Super-Resolution-
SwinFIR28.120.8393SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
MaIR+27.890.8336MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration
MaIR27.710.8305MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration
SwinIR27.450.8254 SwinIR: Image Restoration Using Swin Transformer
HBPN27.30.818Hierarchical Back Projection Network for Image Super-Resolution
LTE27.24-Local Texture Estimator for Implicit Representation Function
SAN27.230.8169Second-Order Attention Network for Single Image Super-Resolution-
CSNLN27.220.8168Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
DRLN+27.140.8149Densely Residual Laplacian Super-Resolution
DBPN-RES-MR64-327.080.814Deep Back-Projection Networks for Single Image Super-resolution
0 of 64 row(s) selected.