CVPR2022论文速递(2022.5.31)!共9篇!

2022-09-02 14:18:52 浏览数 (1)

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

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!

Updated on : 31 May 2022

total number : 9

目标检测 / Object Detection - 1 篇

Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving

标题:Time3D:自动驾驶的端到端联合单目3D对象检测和跟踪

  • 论文/Paper: http://arxiv.org/pdf/2205.14882
  • 代码/Code: None

目标跟踪/Object Tracking - 1 篇

Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving

标题:Time3D:自动驾驶的端到端联合单目3D对象检测和跟踪

  • 论文/Paper: http://arxiv.org/pdf/2205.14882
  • 代码/Code: None

超分/Super-Resolution - 1 篇

ShuffleMixer: An Efficient ConvNet for Image Super-Resolution

标题:Shufflemixer:用于图像超分辨率的高效卷积网络

  • 论文/Paper: http://arxiv.org/pdf/2205.15175
  • 代码/Code: https://github.com/sunny2109/MobileSR-NTIRE2022

视频插帧/Frame Interpolation - 1 篇

IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation

标题:IFRNet:中间特征精炼网络,用于有效的帧插值

  • 论文/Paper: http://arxiv.org/pdf/2205.14620
  • 代码/Code: https://github.com/ltkong218/IFRNet

其他/Other - 6 篇

Pooling Revisited: Your Receptive Field is Suboptimal

标题:Pooling Revisited:你的感受野是次优的

  • 论文/Paper: http://arxiv.org/pdf/2205.15254
  • 代码/Code: None

GraphWalks: Efficient Shape Agnostic Geodesic Shortest Path Estimation

标题:GraphWalks:有效的形状不可知地测量最短路径估计

  • 论文/Paper: http://arxiv.org/pdf/2205.15217
  • 代码/Code: None

The Devil is in the Pose: Ambiguity-free 3D Rotation-invariant Learning via Pose-aware Convolution

标题:在姿势中的恶魔:通过姿势吸引卷积的无歧义3D旋转不变的学习

  • 论文/Paper: http://arxiv.org/pdf/2205.15210
  • 代码/Code: None

Neural Volumetric Object Selection

标题:神经体积对象选择

  • 论文/Paper: http://arxiv.org/pdf/2205.14929
  • 代码/Code: None

From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering

标题:从表征到推理:迈向视频提问的证据和常识性推理

  • 论文/Paper: http://arxiv.org/pdf/2205.14895
  • 代码/Code: https://github.com/bcmi/Causal-VidQA.git

Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors

标题:神经形状匹配:自我监督的物体组件和对抗形状先验

  • 论文/Paper: http://arxiv.org/pdf/2205.14886
  • 代码/Code: None

0 人点赞