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：

SIGGRAPH 2022 | Honorable Mentions 稀疏椭偏法，重建效果接近真实物体！已开源

主页：http://vclab.kaist.ac.kr/siggraph2022p1/index.html 代码：https://github.com/KAIST-VCLAB/SparseEllipsometry

摘要：

提出了稀疏椭偏法，这是一种便携式偏振采集方法，可捕获极化 SVBRDF 和 3D 形状同时进行。我们的手持设备由现成的固定光学元件组成。每个对象的总采集时间不是几天，而是二十到三十分钟。我们开发了一个完整的偏振 SVBRDF 模型，包括漫反射和镜面反射分量，以及单次散射，并设计了一种新的偏振逆渲染算法，通过生成建模对镜面反射样本进行数据增强。我们的结果与最近捕获的真实世界对象的极化 BRDF 的grouth truth 数据集非常一致。

最新论文整理

ECCV2022

Updated on : 13 Jul 2022

total number : 15

Camera Pose Auto-Encoders for Improving Pose Regression

• 论文/Paper: http://arxiv.org/pdf/2207.05530
• 代码/Code: https://github.com/yolish/camera-pose-auto-encoders.

Tracking Objects as Pixel-wise Distributions

• 论文/Paper: http://arxiv.org/pdf/2207.05518
• 代码/Code: None

Compound Prototype Matching for Few-shot Action Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.05515
• 代码/Code: None

Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks

• 论文/Paper: http://arxiv.org/pdf/2207.05444
• 代码/Code: https://github.com/JiehongLin/Self-DPDN.

Synergistic Self-supervised and Quantization Learning

• 论文/Paper: http://arxiv.org/pdf/2207.05432
• 代码/Code: https://github.com/megvii-research/SSQL-ECCV2022.

UniNet: Unified Architecture Search with Convolution, Transformer, and MLP

• 论文/Paper: http://arxiv.org/pdf/2207.05420
• 代码/Code: https://github.com/Sense-X/UniNet.

Knowledge Condensation Distillation

• 论文/Paper: http://arxiv.org/pdf/2207.05409
• 代码/Code: https://github.com/dzy3/KCD.

Frequency Domain Model Augmentation for Adversarial Attack

• 论文/Paper: http://arxiv.org/pdf/2207.05382
• 代码/Code: https://github.com/yuyang-long/ssa

HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors

• 论文/Paper: http://arxiv.org/pdf/2207.05345
• 代码/Code: https://github.com/LutingWang/HEAD

Video Graph Transformer for Video Question Answering

• 论文/Paper: http://arxiv.org/pdf/2207.05342
• 代码/Code: https://github.com/sail-sg/VGT.

CPO: Change Robust Panorama to Point Cloud Localization

• 论文/Paper: http://arxiv.org/pdf/2207.05317
• 代码/Code: None

Contrastive Deep Supervision

• 论文/Paper: http://arxiv.org/pdf/2207.05306
• 代码/Code: None

Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection

• 论文/Paper: http://arxiv.org/pdf/2207.05293
• 代码/Code: https://github.com/MuchHair/HQM.

PseudoClick: Interactive Image Segmentation with Click Imitation

• 论文/Paper: http://arxiv.org/pdf/2207.05282
• 代码/Code: None

Hunting Group Clues with Transformers for Social Group Activity Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.05254
• 代码/Code: None

CVPR2022

Updated on : 13 Jul 2022

total number : 3

1st Place Solution to the EPIC-Kitchens Action Anticipation Challenge 2022

• 论文/Paper: http://arxiv.org/pdf/2207.05730
• 代码/Code: None

Tell Me the Evidence? Dual Visual-Linguistic Interaction for Answer Grounding

• 论文/Paper: http://arxiv.org/pdf/2207.05703
• 代码/Code: None

Scaling Novel Object Detection with Weakly Supervised Detection Transformers

• 论文/Paper: http://arxiv.org/pdf/2207.05205
• 代码/Code: None