ICCV 2023 超分辨率(Super-Resolution)论文汇总

文章目录


图像超分辨率(Image Super-Resolution)

1、经典图像超分辨率(Classical image SR)

1. Dual Aggregation Transformer for Image Super-Resolution(上交,ETH Yulun Zhang团队)

2. Feature Modulation Transformer: Cross-Refinement of Global Representation via High-Frequency Prior for Image Super-Resolution(成电 张乐团队)

3. Boosting Single Image Super-Resolution via Partial Channel Shifting(西南交通)

4. MSRA-SR: Image Super-resolution Transformer with Multi-scale Shared Representation Acquisition(中科大,自动化所 赫然、谭铁牛团队)

5. Content-Aware Local GAN for Photo-Realistic Super-Resolution(首尔大学 Sanghyun Son、Kyoung Mu Lee团队)

6. SRFormer: Permuted Self-Attention for Single Image Super-Resolution(南开 程明明团队,字节)

2、基于参考的图像超分辨率(Reference-Based image SR)

1. LMR: A Large-Scale Multi-Reference Dataset for Reference-Based Super-Resolution(自动化所 张兆翔团队,百度)

3、高效&轻量化图像超分辨率(Efficient/Lightweight image SR)

1. SPIN | Lightweight Image Super-Resolution with Superpixel Token Interaction(中山大学 任文琦、操晓春团队)

2. ISS-P | Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution(RIT Zhiqiang Tao团队,ETH Yulun Zhang团队)

3. Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution(清华 王斌团队,快手)

4. Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution(南京理工 潘金山团队)

5. DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution(南京理工 潘金山团队)

4、盲超分/真实世界图像超分辨率(Blind/Real-world image SR)

1. MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces(哈工大 刘明、左旺孟团队)

2. DARSR | Learning Correction Filter via Degradation-Adaptive Regression for Blind Single Image Super-Resolution(北科大 祝晓斌团队)

Burst SR

(个人感觉Burst SR可以归于真实世界超分辨率下面)

3. Self-Supervised Burst Super-Resolution(ETH Van Gool,Adobe)

4. FBANet | Towards Real-World Burst Image Super-Resolution: Benchmark and Method(中山大学 林倞团队,北大 陈杰)

5、超分辨率应用(Application of SR)

(1)医学图像(Medical image)

1. McASSR | Rethinking Multi-Contrast MRI Super-Resolution: Rectangle-Window Cross-Attention Transformer and Arbitrary-Scale Upsampling(浙大)

2. MC-VarNet | Decomposition-Based Variational Network for Multi-Contrast MRI Super-Resolution and Reconstruction(华东师范 方发明团队)

3. CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution(中山大学 谢晓华团队)

(2)遥感/高光谱图像(Hyperspectral image)

4. HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models(西工大 李映团队)

5. ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution(西电 Chi Zhang团队,重邮 高新波,悉尼大学)

(3)文本图像(Text image)

6. A Benchmark for Chinese-English Scene Text Image Super-resolution(香港理工 Lei Zhang,OPPO)

(4)光场图像(Light Field image)

7. Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution(国防科大 杨俊刚、王应谦团队,空军航空大学 王龙光)

(5)深度图(Depth Map)

8. Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution(西交 张讲社团队,ETH Yulun Zhang、Radu Timofte、Van Gool团队)

视频超分辨率(Video Super-Resolution)

包括普通视频超分辨率与时空视频超分辨率

1. MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution(台湾阳明交通大学 Wen-Hsiao Peng团队)

2. Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution(西交 钱学明团队,微软亚研 杨欢团队)

3. Multi-Frequency Representation Enhancement with Privilege Information for Video Super-Resolution(农大 李振波团队,三星)

参考:

ICCV 2023 Open Access Repository

ICCV 2023 超分辨率(Super-Resolution)论文汇总 - 知乎

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

JOYCE_Leo16

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值