超级会员免费看
本文探讨了视频超分辨率领域的两项研究——TDAN和EDSR。TDAN提出了一种时空可变形对齐网络，用于解决参考帧和支持帧之间的不匹配问题。而EDSR则通过优化残差网络架构，简化网络并提高图像超分辨率性能。此外，还提到了数据增强、大型字典和分层搜索等提升超分辨率效果的方法，并分享了两个相关项目，包括基于生成对抗网络的超分辨率实现。
Tian Y, Zhang Y, Fu Y, et al. Tdan: Temporally-deformable alignment network for video super-resolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 3360-3369.
Paper: Tdan
Tdan: Temporally-deformable alignment network for video super-resolution
Summary
- propose a temporally-deformable alignment network(TDAN) to
adaptively align the reference frame and each supporting frame a the feature level without computing optical flow. - use features from both the reference frame and each supporting frame to
dynamically predict offsets of sampling convolution kernels
订阅专栏 解锁全文
扫一扫
8万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
