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
ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer
标题:ObjectFolder 2.0:SIM2REAL TRANSER的多句子对象数据集
Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation
标题:通过弹性响应蒸馏克服灾难性遗忘
Arbitrary-Scale Image Synthesis
标题:任意尺度图像合成
Multi-View Transformer for 3D Visual Grounding
标题:用于3D视觉接地的多视图变压器
Dual-AI: Dual-path Action Interaction Learning for Group Activity Recognition
标题:双AI:组活动识别的双路径交互学习
Detector-Free Weakly Supervised Group Activity Recognition
标题:探测器无弱监督集团活动识别
Text Spotting Transformers
标题:文本拍摄变形金刚
P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior
标题:p3depth:先前的分段平面单曲深度估计
Rethinking Visual Geo-localization for Large-Scale Applications
标题:重新思考大规模应用的视觉地理定位
IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images
标题:铁:通过从光度图像优化神经系统和材料来实现逆渲染
SNUG: Self-Supervised Neural Dynamic Garments
标题:舒适:自我监督的神经动态服装
Leveraging Equivariant Features for Absolute Pose Regression
标题:绝对姿势回归利用等分意识的功能
MonoTrack: Shuttle trajectory reconstruction from monocular badminton video
标题:Monotrack:单眼羽毛球视频的梭轨迹重建
Revisiting Near/Remote Sensing with Geospatial Attention
标题:在地理空间关注重新审视/遥感