Stars
Techniques for deep learning with satellite & aerial imagery
PyTorch code and models for the DINOv2 self-supervised learning method.
Enabling the Windows Subsystem for Linux to include support for Wayland and X server related scenarios
Implementation of One-Shot Object Detection with Co-Attention and Co-Excitation in Pytorch
FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.
A playbook for systematically maximizing the performance of deep learning models.
Differentiable rendering without approximation.
Blender python script to create a 3D scene with customizable subject, camera, environment options.
A Python library for parsing MISB ST 0601 Key Length Value (KLV) metadata.
jMISB is an open source Java library implementing various MISB standards.
The WeightWatcher tool for predicting the accuracy of Deep Neural Networks
Leading free and open-source face recognition system
Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Reference implementation of the Visual Tracking eXchange protocol.
RPT: Learning Point Set Representation for Siamese Visual Tracking
Dense reppoints: Representing visual objects with dense point sets https://arxiv.org/abs/1912.11473
Official implementation of "Implicit Neural Representations with Periodic Activation Functions"
BANMo Building Animatable 3D Neural Models from Many Casual Videos
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)
COLMAP - Structure-from-Motion and Multi-View Stereo
Visual tracking library based on PyTorch.
fastdup is a powerful free tool designed to rapidly extract valuable insights from your image & video datasets. Assisting you to increase your dataset images & labels quality and reduce your data o…
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots