CVPR2022论文速递（2022.4.1）！共33篇,已分类!
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
欢迎关注：
大家好, 最近正在优化每周分享的CVPR论文, 目前考虑按照不同类别去分类,方便不同方向的小伙伴挑选自己感兴趣的论文哈
欢迎大家留言其他想法, 合适的话会采纳哈! 求个三连支持一波哈
目标检测 / Object Detection - 1 篇
Multi-Granularity Alignment Domain Adaptation for Object Detection
论文/Paper: http://arxiv.org/pdf/2203.16897
代码/Code: None
目标跟踪/Object Tracking - 1 篇
MeMOT: Multi-Object Tracking with Memory
论文/Paper: http://arxiv.org/pdf/2203.16761
代码/Code: None
语义分割/Segmentation - 1 篇
ReSTR: Convolution-free Referring Image Segmentation Using Transformers
论文/Paper: http://arxiv.org/pdf/2203.16768
代码/Code: None
GAN - 2 篇
TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing
论文/Paper: http://arxiv.org/pdf/2203.17266
代码/Code: https://github.com/BillyXYB/TransEditor
TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing
论文/Paper: http://arxiv.org/pdf/2203.17266
代码/Code: https://github.com/BillyXYB/TransEditor
Transformers - - 5 篇
TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing
论文/Paper: http://arxiv.org/pdf/2203.17266
代码/Code: https://github.com/BillyXYB/TransEditor
VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers
论文/Paper: http://arxiv.org/pdf/2203.17247
代码/Code: None
CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
论文/Paper: http://arxiv.org/pdf/2203.16896
代码/Code: None
Deformable Video Transformer
论文/Paper: http://arxiv.org/pdf/2203.16795
代码/Code: None
ReSTR: Convolution-free Referring Image Segmentation Using Transformers
论文/Paper: http://arxiv.org/pdf/2203.16768
代码/Code: None
多模态 / Multimodal - 1 篇
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
论文/Paper: http://arxiv.org/pdf/2203.16778
代码/Code: None
姿态估计/Pose Estimation - 1 篇
Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions
论文/Paper: http://arxiv.org/pdf/2203.17234
代码/Code: None
对比学习/Contrastive Learning - 1 篇
Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization
论文/Paper: http://arxiv.org/pdf/2203.16800
代码/Code: https://github.com/MengyuanChen21/CVPR2022-FTCL
人脸相关 / Face - 3 篇
TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing
论文/Paper: http://arxiv.org/pdf/2203.17266
代码/Code: https://github.com/BillyXYB/TransEditor
Face Relighting with Geometrically Consistent Shadows
论文/Paper: http://arxiv.org/pdf/2203.16681
代码/Code: None
Escaping Data Scarcity for High-Resolution Heterogeneous Face Hallucination
论文/Paper: http://arxiv.org/pdf/2203.16669
代码/Code: None
视频插帧/Frame Interpolation - 1 篇
Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusion
论文/Paper: http://arxiv.org/pdf/2203.17191
代码/Code: None
车道线检测/Lane Detection - 1 篇
Towards Driving-Oriented Metric for Lane Detection Models
论文/Paper: http://arxiv.org/pdf/2203.16851
代码/Code: None
点云/Point Clouds - 3 篇
Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds
论文/Paper: http://arxiv.org/pdf/2203.16895
代码/Code: None
Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds
论文/Paper: http://arxiv.org/pdf/2203.16895
代码/Code: None
Learning Local Displacements for Point Cloud Completion
论文/Paper: http://arxiv.org/pdf/2203.16600
代码/Code: None
其他/Other - 17 篇
Bringing Old Films Back to Life
论文/Paper: http://arxiv.org/pdf/2203.17276
代码/Code: https://github.com/raywzy/Bringing-Old-Films-Back-to-Life
Generating High Fidelity Data from Low-density Regions using Diffusion Models
论文/Paper: http://arxiv.org/pdf/2203.17260
代码/Code: None
Continuous Scene Representations for Embodied AI
论文/Paper: http://arxiv.org/pdf/2203.17251
代码/Code: None
SimVQA: Exploring Simulated Environments for Visual Question Answering
论文/Paper: http://arxiv.org/pdf/2203.17219
代码/Code: None
Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy
论文/Paper: http://arxiv.org/pdf/2203.17205
代码/Code: None
AEGNN: Asynchronous Event-based Graph Neural Networks
论文/Paper: http://arxiv.org/pdf/2203.17149
代码/Code: None
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
论文/Paper: http://arxiv.org/pdf/2203.17008
代码/Code: None
Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond
论文/Paper: http://arxiv.org/pdf/2203.16931
代码/Code: None
End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps
论文/Paper: http://arxiv.org/pdf/2203.16910
代码/Code: None
Reflection and Rotation Symmetry Detection via Equivariant Learning
论文/Paper: http://arxiv.org/pdf/2203.16787
代码/Code: None
Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models
论文/Paper: http://arxiv.org/pdf/2203.16755
代码/Code: None
Personalized Image Aesthetics Assessment with Rich Attributes
论文/Paper: http://arxiv.org/pdf/2203.16754
代码/Code: None
Constrained Few-shot Class-incremental Learning
论文/Paper: http://arxiv.org/pdf/2203.16588
代码/Code: None
Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation
论文/Paper: http://arxiv.org/pdf/2203.16586
代码/Code: None
Exploiting Explainable Metrics for Augmented SGD
论文/Paper: http://arxiv.org/pdf/2203.16723
代码/Code: None
Task Adaptive Parameter Sharing for Multi-Task Learning
论文/Paper: http://arxiv.org/pdf/2203.16708
代码/Code: None
D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions
论文/Paper: http://arxiv.org/pdf/2112.03028
代码/Code: None