论文/代码速递2022.11.28！

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：

标题：ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision

主页：https://gerwang.github.io/shadowneus/

摘要：

通过监督场景和多视图图像平面之间的相机光线，NeRF 为新视图合成任务重建神经场景表示。另一方面，光源和场景之间的阴影光线还有待考虑。因此，我们提出了一种新颖的阴影射线监督方案，可以优化沿射线的样本和射线位置。通过监督阴影光线，我们在多种光照条件下成功地从单视图纯阴影或 RGB 图像重建场景的神经 SDF。

最新论文整理

ECCV2022

Updated on : 28 Nov 2022

total number : 2

Cross-Domain Ensemble Distillation for Domain Generalization

• 论文/Paper: http://arxiv.org/pdf/2211.14058
• 代码/Code: http://github.com/leekyungmoon/XDED

Real-Time Under-Display Cameras Image Restoration and HDR on Mobile Devices

• 论文/Paper: http://arxiv.org/pdf/2211.14040
• 代码/Code: None

CVPR2022

NeurIPS

Updated on : 28 Nov 2022

total number : 7

Towards Hard-pose Virtual Try-on via 3D-aware Global Correspondence Learning

• 论文/Paper: http://arxiv.org/pdf/2211.14052
• 代码/Code: None

Cross Aggregation Transformer for Image Restoration

• 论文/Paper: http://arxiv.org/pdf/2211.13654
• 代码/Code: https://github.com/zhengchen1999/CAT

Delving into Out-of-Distribution Detection with Vision-Language Representations

• 论文/Paper: http://arxiv.org/pdf/2211.13445
• 代码/Code: https://github.com/deeplearning-wisc/MCM.

CGOF++: Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields

• 论文/Paper: http://arxiv.org/pdf/2211.13251
• 代码/Code: None

Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?

• 论文/Paper: http://arxiv.org/pdf/2211.13972
• 代码/Code: None

Towards Practical Control of Singular Values of Convolutional Layers

• 论文/Paper: http://arxiv.org/pdf/2211.13771
• 代码/Code: https://github.com/WhiteTeaDragon/practical_svd_conv

Improving dermatology classifiers across populations using images generated by large diffusion models

• 论文/Paper: http://arxiv.org/pdf/2211.13352
• 代码/Code: None