CVPR2022论文速递（2022.3.15）！共21篇，含人脸超分/图像修复/talk head等多篇成果...

整理：AI算法与图像处理，分享请注明出处

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

欢迎关注：

GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors

• 论文/Paper：https://arxiv.org/abs/2203.07319

• 代码/Code：

RCL: Recurrent Continuous Localization for Temporal Action Detection

• 论文/Paper：https://arxiv.org/abs/2203.07112

• 代码/Code：

Active Learning by Feature Mixing

• 论文/Paper：https://arxiv.org/abs/2203.07034

• 代码/Code：

Rethinking Minimal Sufficient Representation in Contrastive Learning

• 论文/Paper：https://arxiv.org/abs/2203.07004

• 代码/Code：https://github.com/Haoqing-Wang/InfoCL

Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots

• 论文/Paper：https://arxiv.org/abs/2203.06967

• 代码/Code：https://github.com/demonsjin/Blind2Unblind

UniVIP: A Unified Framework for Self-Supervised Visual Pre-training

• 论文/Paper：https://arxiv.org/abs/2203.06965

• 代码/Code：

Forward Compatible Few-Shot Class-Incremental Learning

• 论文/Paper：https://arxiv.org/abs/2203.06953

• 代码/Code：https://github.com/zhoudw-zdw/CVPR22-Fact

XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding

• 论文/Paper：https://arxiv.org/abs/2203.06947

• 代码/Code：

Accelerating DETR Convergence via Semantic-Aligned Matching

• 论文/Paper：https://arxiv.org/abs/2203.06883

• 代码/Code：https://github.com/ZhangGongjie/SAM-DETR

ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation

• 论文/Paper：https://arxiv.org/abs/2203.06811

• 代码/Code：

Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs

• 论文/Paper：https://arxiv.org/abs/2203.06717

• 代码/Code：https://github.com/megvii-research/RepLKNet

LAS-AT: Adversarial Training with Learnable Attack Strategy

• 论文/Paper：https://arxiv.org/abs/2203.06616

• 代码/Code：https://github.com/jiaxiaojunQAQ/LAS-AT

Depth-Aware Generative Adversarial Network for Talking Head Video Generation

• 论文/Paper：https://arxiv.org/abs/2203.06605

• 代码/Code：https://github.com/harlanhong/CVPR2022-DaGAN

AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation

• 论文/Paper：https://arxiv.org/abs/2203.06558

• 代码/Code：

Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning

• 论文/Paper：https://arxiv.org/abs/2203.06541

• 代码/Code：https://github.com/Jiahao-UTS/SLPT-master

Kernel Proposal Network for Arbitrary Shape Text Detection

• 论文/Paper：https://arxiv.org/abs/2203.06410

• 代码/Code：https://github.com/GXYM/KPN

SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection

• 论文/Paper：https://arxiv.org/abs/2203.06398

• 代码/Code：https://github.com/CityU-AIM-Group/SIGMA

Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning

• 论文/Paper：https://arxiv.org/abs/2203.06359

• 代码/Code：

Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation

• 论文/Paper：https://arxiv.org/abs/2203.06321

• 代码/Code：

MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting

• 论文/Paper：https://arxiv.org/abs/2203.06304

• 代码/Code：https://github.com/tsingqguo/misf