论文速递2022.9.26！

整理：AI算法与图像处理

CVPR2022论文和代码整理：https://github.com/DWCTOD/CVPR2022-Papers-with-Code-Demo

ECCV2022论文和代码整理：https://github.com/DWCTOD/ECCV2022-Papers-with-Code-Demo

最新成果demo展示：

关联视频：https://www.bilibili.com/video/BV1nf4y1F7bz/ https://www.bilibili.com/video/BV15P4y1E7Mv/

作者原话：我正在尝试从单个草图实时自动生成插图、动画和 3D 模型。

您可以使用 UI 上的滑块更改零件的形状、颜色和纹理，也可以随机选择它们。

我们的目标是创建一个系统，帮助从事创意活动的人们，从创作者到以前从未画过画的人

最新论文整理

ECCV2022

Updated on : 27 Sep 2022

total number : 4

Real-RawVSR: Real-World Raw Video Super-Resolution with a Benchmark Dataset

• 论文/Paper: http://arxiv.org/pdf/2209.12475
• 代码/Code: https://github.com/zmzhang1998/Real-RawVSR.

ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement

• 论文/Paper: http://arxiv.org/pdf/2209.12213
• 代码/Code: None

Leveraging Self-Supervised Training for Unintentional Action Recognition

• 论文/Paper: http://arxiv.org/pdf/2209.11870
• 代码/Code: None

Contour Dice loss for structures with Fuzzy and Complex Boundaries in Fetal MRI

• 论文/Paper: http://arxiv.org/pdf/2209.12232
• 代码/Code: None

CVPR2022

NeurIPS

Updated on : 27 Sep 2022

total number : 6

SAPA: Similarity-Aware Point Affiliation for Feature Upsampling

• 论文/Paper: http://arxiv.org/pdf/2209.12866
• 代码/Code: https://github.com/poppinace/sapa

Rethinking Resolution in the Context of Efficient Video Recognition

• 论文/Paper: http://arxiv.org/pdf/2209.12797
• 代码/Code: https://github.com/CVMI-Lab/ResKD.

Multi-dataset Training of Transformers for Robust Action Recognition

• 论文/Paper: http://arxiv.org/pdf/2209.12362
• 代码/Code: https://github.com/JunweiLiang/MultiTrain

Paraphrasing Is All You Need for Novel Object Captioning

• 论文/Paper: http://arxiv.org/pdf/2209.12343
• 代码/Code: None

Personalizing Text-to-Image Generation via Aesthetic Gradients

• 论文/Paper: http://arxiv.org/pdf/2209.12330
• 代码/Code: https://github.com/vicgalle/stable-diffusion-aesthetic-gradients

Optimal Transport-based Identity Matching for Identity-invariant Facial Expression Recognition

• 论文/Paper: http://arxiv.org/pdf/2209.12172
• 代码/Code: https://github.com/kdhht2334/ELIM_FER.