HyperAI
HyperAI초신경
홈
플랫폼
문서
뉴스
연구 논문
튜토리얼
데이터셋
백과사전
SOTA
LLM 모델
GPU 랭킹
컨퍼런스
전체 검색
소개
한국어
HyperAI
HyperAI초신경
Toggle sidebar
전체 사이트 검색...
⌘
K
Command Palette
Search for a command to run...
홈
SOTA
이미지 초해상화
Image Super Resolution On Bsd100 4X Upscaling
Image Super Resolution On Bsd100 4X Upscaling
평가 지표
PSNR
SSIM
평가 결과
이 벤치마크에서 각 모델의 성능 결과
Columns
모델 이름
PSNR
SSIM
Paper Title
Repository
DRCT-L
28.16
0.7577
DRCT: Saving Image Super-resolution away from Information Bottleneck
Hi-IR-L
28.13
0.7622
Hierarchical Information Flow for Generalized Efficient Image Restoration
-
HMA†
28.13
0.7562
HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
HAT-L
28.09
0.7551
Activating More Pixels in Image Super-Resolution Transformer
HAT_FIR
28.07
-
SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
DRCT
28.06
0.7533
DRCT: Saving Image Super-resolution away from Information Bottleneck
CPAT+
28.06
0.7532
Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution
-
HAT
28.05
0.7534
Activating More Pixels in Image Super-Resolution Transformer
CPAT
28.04
0.7527
Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution
-
SwinFIR
28.03
0.7520
SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
WaveMixSR-V2
27.87
0.764
WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency
DRLN+
27.87
0.7453
Densely Residual Laplacian Super-Resolution
LTE
27.86
-
Local Texture Estimator for Implicit Representation Function
SAN
27.86
0.7457
Second-Order Attention Network for Single Image Super-Resolution
-
HAN+
27.85
0.7454
Single Image Super-Resolution via a Holistic Attention Network
SRGAN + Residual-in-Residual Dense Block
27.85
0.7455
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
RFN
27.83
-
Progressive Perception-Oriented Network for Single Image Super-Resolution
ABPN
27.82
0.743
Image Super-Resolution via Attention based Back Projection Networks
CSNLN
27.8
0.7439
Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
ProSR
27.79
-
A Fully Progressive Approach to Single-Image Super-Resolution
0 of 71 row(s) selected.
Previous
Next