ICCV 2021
- ICCV2021官網(wǎng)：https://iccv2021.thecvf.com/
- ICCV2021完整論文列表：https://openaccess.thecvf.com/ICCV2021
- 開(kāi)會(huì)時(shí)間：2021年10月11日-10月17日
- Demo 搬運(yùn)：https://space.bilibili.com/288489574
Super-Resolution
- 圖像超分辨率
- Attention-Based Multi-Reference Learning for Image Super-Resolution
- Learning a Single Network for Scale-Arbitrary Super-Resolution
- 論文：http://arxiv.org/abs/2004.03791
- 代碼：https://github.com/LongguangWang/ArbSR
- 描述：scale-arbitrary 任意縮放
- Achieving On-Mobile Real-Time Super-Resolution With Neural Architecture and Pruning Search
- 論文：http://arxiv.org/abs/2108.08910
- 代碼：
- 描述：real-time, NAS
- Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
- 論文：http://arxiv.org/abs/2103.14006
- 代碼：
- 描述：Blind SR
- Event Stream Super-Resolution via Spatiotemporal Constraint Learning
- 論文：openaccess.thecvf.com
- 代碼：
- 描述：event stream SR
- Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution
- 論文：openaccess.thecvf.com
- 代碼：
- 描述：attention
- Context Reasoning Attention Network for Image Super-Resolution
- 論文：openaccess.thecvf.com
- 代碼：
- 描述：attention
- EvIntSR-Net: Event Guided Multiple Latent Frames Reconstruction and Super-Resolution
- 論文：openaccess.thecvf.com
- 代碼：
- 描述：EventSR
- Demo：AI視頻修復(fù)椰苟！基于Event引導(dǎo)的視頻幀重建和超分辨率 ICCV2021
- Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
- 論文：http://arxiv.org/abs/2108.05302
- 代碼：https://github.com/JingyunLiang/MANet
- 描述：blind SR
- Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective
- 論文：openaccess.thecvf.com
- 代碼：
- 描述：unpaired realSR
- Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
- 論文：http://arxiv.org/abs/2108.05301
- 代碼：https://github.com/JingyunLiang/HCFlow
- 描述：SR/Rescale
- Learning Frequency-aware Dynamic Network for Efficient Super-Resolution
- 論文：http://arxiv.org/abs/2103.08357
- 代碼：
- 描述：Efficient SR
- Dual-Camera Super-Resolution With Aligned Attention Modules
- 論文：openaccess.thecvf.com
- 代碼：
- 描述：dual camera SR
- Manifold Matching via Deep Metric Learning for Generative Modeling
- 論文：https://arxiv.org/abs/2106.10777
- 代碼：https://github.com/dzld00/pytorch-manifold-matching.git
- 描述：Manifold Matching
- Burst SR
- Deep Reparametrization of Multi-Frame Super-Resolution and Denoising
- 論文：http://arxiv.org/abs/2108.08286
- 代碼：https://github.com/goutamgmb/deep-rep
- 描述：Multi-Frame
- Lucas-Kanade Reloaded: End-to-End Super-Resolution From Raw Image Bursts
- 論文：http://arxiv.org/abs/2104.06191
- 代碼：https://github.com/bruno-31/lkburst
- 描述：Raw Image Bursts SR
- 視頻超分辨率
- Omniscient Video Super-Resolution
- 論文：http://arxiv.org/abs/2004.03791
- 代碼：
- 描述：VSR
- COMISR: Compression-Informed Video Super-Resolution
- 論文：http://arxiv.org/abs/2105.01237
- 代碼：https://github.com/google-research/google-research/tree/master/comisr
- 描述：VSR
- Deep Blind Video Super-Resolution
- 論文：openaccess.thecvf.com
- 代碼：
- 描述：Blind VSR
- Real-World Video Super-Resolution: A Benchmark Dataset and a Decomposition Based Learning Scheme
- 論文：openaccess.thecvf.com
- 代碼：https://github.com/IanYeung/RealVSR
- 描述：RealVSR dataset
- Efficient Video Compression via Content-Adaptive Super-Resolution
- 論文：http://arxiv.org/abs/2104.02322
- 代碼：
- 描述：Video Compression
- Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation
- 論文：https://arxiv.org/abs/2108.08202
- 代碼：https://github.com/Neural-video-delivery/CaFM-Pytorch-ICCV2021
- 描述：Video Delivery
- 其他
- Fourier Space Losses for Efficient Perceptual Image Super-Resolution
- 論文：http://arxiv.org/abs/2106.00783
- 代碼：
- 描述：loss
- Benchmarking Ultra-High-Definition Image Super-Resolution
- 論文：openaccess.thecvf.com
- 代碼：
- 描述：UHD SR dataset, 4K, 8K,
