WU-CVGL / MBA-SLAM

"MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation"
https://arxiv.org/abs/2411.08279
51 stars 1 forks source link
bundle-adjustment deblur gaussian-splatting nerf slam

MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation

arXiv 2024

[![arXiv](https://img.shields.io/badge/ArXiv-2411.08279-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2411.08279) [![Project page](https://img.shields.io/badge/Project-Page-brightgreen)](https://wangpeng000.github.io/MBA-SLAM/) ## Overview

Overview

Given a sequence of severe motion blurred images and depth, MBA-SLAM can accurately estimate the local camera motion trajectory of each blurred image within the exposure time and recovers the high quality 3D scene. ## Pipeline

Pipeline

Tracking: Our motion blur-aware tracker directly estimates the camera motion trajectory during the exposure time. Mapping: Our mapper generates virtual sharp images along the camera trajectory.