Main articles I read or plan to read, as well as useful links.
- read
- glance
- plan to read
https://paperswithcode.com/task/3d-human-pose-estimation - comparison
https://github.com/trumDog/3d-human-pose-estimation - more information and articles
-
3D human pose estimation in video with temporal convolutions and semi-supervised training (cvpr2019)
-
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training (aaai2020)
-
GAST-Net: Graph Attention Spatio-temporal Convolutional Networks for 3D Human Pose Estimation in Video (arXiv2020)
-
Motion Guided 3D Pose Estimation from Videos (eccv2020)
[paper]
-
Learning Monocular 3D Human Pose Estimation from Multi-view Images (CVPR2018)
[paper][code][project]
https://paperswithcode.com/sota/pose-tracking-on-posetrack2017 - comparison https://posetrack.net/leaderboard.php - main liderboard
-
15 Keypoints Is All You Need (cvpr 2020)
[paper] [code]
-
LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking
-
Efficient Online Multi-Person 2D Pose Tracking with (cvpr 2019) Recurrent Spatio-Temporal Affinity Fields
[paper] [code]
-
Combining detection and tracking for human pose estimation in videos
[paper] [code]
-
BlazePose: On-device Real-time Body Pose tracking (google 2020)
-
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (CycleGAN) (cvpr 2020)
-
U-GAT-IT: UNSUPERVISED GENERATIVE ATTENTIONAL NETWORKS WITH ADAPTIVE LAYERINSTANCE NORMALIZATION FOR IMAGE TO-IMAGE TRANSLATION
-
Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation
https://github.com/TheDetial/Super-Resolution - more articles
-
High-Quality 3D Reconstruction With Depth Super-Resolution and Completion
[paper] [code]
-
Channel Attention based Iterative Residual Learning for Depth Map Super-Resolution
[paper] [code]
-
Simultaneously Color-Depth Super-Resolution with Conditional Generative Adversarial Network
[paper] [code]
-
Multi-Scale Progressive Fusion Learning for Depth Map Super-Resolution
[paper] [code]
-
Feedback Network for Image Super-Resolution
[paper] [code]
-
Deep Depth Completion of a Single RGB-D Image
[paper] [code]
-
Learning Guided Convolutional Network for Depth Completion
[paper] [code]
To learn image super-resolution, use a GAN to learn how to do image degradation first [paper] [code]
-
Deep High-Resolution Representation Learning for Human Pose Estimation
-
Deep Surface Normal Estimation with Hierarchical RGB-D Fusion
[paper] [code]
-
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Transformers understanding and with code
- How GPT3 Works - Visualizations and Animations, The Illustrated BERT, ELMo, and co.
- Transformers pythorch
- GAN series
- Object detection
- Only Numpy: Implementing Convolutional Neural Network using Numpy
- Быстрая свертка по методу Шмуэля Винограда
- Вычислительная фотография
- Лекции NLA
- ML, DL and other lectures
- Understanding the backward pass through Batch Normalization Layer
- Collection of the best ML resources by topic
- The Entire Computer Science Curriculum in 1000 YouTube Videos
- GCN understanding