Stars
MTR: Motion Transformer with Global Intention Localization and Local Movement Refinement, NeurIPS 2022.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
An extension of Open3D to address 3D Machine Learning tasks
PyTorch code for training EfficientLPS for LiDAR panoptic segmentation. https://rl.uni-freiburg.de/research/lidar-panoptic
4D Radar Object Detection for Autonomous Driving in Various Weather Conditions
Methods for alignment of global image statistics aimed at unsupervised Domain Adaptation and Data Augmentation
Set up your GitHub Actions workflow with a specific version of Python
Official PyTorch implementation of SegFormer
Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the came…
🚀 A neural network for monocular spacecraft 6D pose estimation: 3rd place solution of the European Space Agency’s pose estimation challenge
Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
Bringing Old Photo Back to Life (CVPR 2020 oral)
Methods for alignment of global image statistics aimed at unsupervised Domain Adaptation and Data Augmentation
A toy implementation of monocular SLAM written while livestreaming
Visual inertial SLAM using stereo cameras, IMU and Extended Kalman Filter
Simultaneous Localization and Mapping using Extended Kalman Filter
A cross-platform command-line utility that creates projects from cookiecutters (project templates), e.g. Python package projects, C projects.
Repo for the paper "GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects"
Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
Image augmentation library in Python for machine learning.
A new kind of Progress Bar, with real-time throughput, ETA, and very cool animations!
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Python sample codes for robotics algorithms.