A toolbox for mapping and localization with line features.

LiveScan3D is a system designed for real time 3D reconstruction using multiple Azure Kinect or Kinect v2 depth sensors simultaneously at real time speed.

Code release for CVPR'24 submission 'OmniGlue'

Distributed and Graph-based Structure from Motion. This project includes the official implementation of our Pattern Recognition 2020 paper: Graph-Based Parallel Large Scale Structure from Motion.

Massively Parallel Multiview Stereopsis by Surface Normal Diffusion

[CVPR 2025 Highlight] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affine Corrections of Monocular Depth Priors"

[NeurIPS 2023] Code for "Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives"

[T-PAMI 2025] DiffMVS & CasDiffMVS

a Pytorch library for multi-view 3D understanding and generation

open source 3D computer vision library

Research tools for autonomous systems in Python

🔥AttSets in Tensorflow (IJCV 2019)

Fast-paced lectures to familiarize new entrants to the lab with key areas in robotics — perception, navigation, control, and learning.

SteamVR Compatible Motion Controller with ESP8266 and Raspberry Pi

Images dataset for 3D reconstruction

Optical multi-view motion capture with calibration suite

PixCuboid: Room Layout Estimation from Multi-view Featuremetric Alignment

This work generates 2D and 3D landmark labels from videos with only two or three uncalibrated, handheld cameras moving in the wild. NeurIPS 2022.

The EYELib: A matlab-python library for Single View Metrology and auto-calibration algorithms and methods

a library that clusters set of images with poses into clusters for easier mvs