tapnet
Point tracker
A deep learning project for tracking points in video sequences
Tracking Any Point (TAP)
1k stars
30 watching
130 forks
Language: Jupyter Notebook
last commit: 3 months ago benchmarkcomputer-visiondeep-learningpoint-trackingrobotics
Related projects:
| Repository | Description | Stars |
|---|---|---|
| google-deepmind/tree | A library for working with nested data structures in Python | 948 |
| google-deepmind/jraph | A lightweight library for working with graph neural networks in jax. | 1,380 |
 catalyst-team/alchemy | Provides tools and infrastructure to log and visualize experiments in deep learning research | 50 |
 scottworkman/deephorizon | A Python-based implementation of computer vision algorithms for detecting and tracking horizon lines in images and videos | 38 |
 yangyanli/pointcnn | A deep learning framework for processing 3D point cloud data to extract relevant features for classification and segmentation tasks. | 1,388 |
 xinli-zn/tadt | A MATLAB implementation of a target-aware tracking algorithm for object detection and tracking in visual sequences | 67 |
| google-deepmind/meltingpot | Assesses generalization of multi-agent reinforcement learning algorithms to novel social situations | 637 |
| google-deepmind/dm_pix | An image processing library built on top of JAX to provide optimized and parallelized functions for machine learning research. | 395 |
| google-deepmind/functa | A repository containing code for a meta-learning experiment on image datasets | 150 |
 pinperepette/geotweet_gui | A tool for tracking and analyzing geolocated social media activity | 119 |
 whotracksme/whotracks.me | An online tracking dataset with metadata and API for analysis | 427 |
 uphyca/galette | An Android plugin that tracks user interactions with Google Analytics | 233 |
 google/allocation-instrumenter | An agent that rewrites bytecode to track memory allocation in Java programs | 483 |
 mpatacchiola/deepgaze | A computer vision library for detecting and tracking human presence in images and videos using convolutional neural networks. | 1,800 |
| google-deepmind/chex | A set of utilities for writing reliable JAX code | 797 |