Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)

pySLAM contains a monocular Visual Odometry (VO) pipeline in Python. It supports many modern local features based on Deep Learning.

Pytorch version of SfmLearner from Tinghui Zhou et al.

TensorFlow Graphics: Differentiable Graphics Layers for TensorFlow

A toolkit for developing and comparing reinforcement learning algorithms.

Tensorflow 1.15 implementation of BSP-NET, along with other scripts used in our paper.

SLAM is mainly divided into two parts: the front end and the back end. The front end is the visual odometer (VO), which roughly estimates the motion of the camera based on the information of adjace…

Caffe: a fast open framework for deep learning.

SLAM performance evaluation framework

BRICS_3D - 3D Perception and Modeling Library

The code for paper "BAE-NET: Branched Autoencoder for Shape Co-Segmentation".

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

A Versatile and Accurate Monocular SLAM